初始化项目,由ModelHub XC社区提供模型

Model: TaH-plus/qwen3-1.7b-tah-duo-maxiter4-amteam121k-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-30 19:04:20 +08:00
commit 6878415ec5
534 changed files with 5477276 additions and 0 deletions

View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

View File

@@ -0,0 +1,85 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

View File

@@ -0,0 +1,60 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151643,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 16384
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 32
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,33 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
aime25_0,0.844,27,32,16384.00
aime25_1,0.062,2,32,16383.78
aime25_2,0.688,22,32,16384.00
aime25_3,0.344,11,32,16384.00
aime25_4,0.000,0,32,16383.97
aime25_5,0.812,26,32,16383.97
aime25_6,0.000,0,32,16383.97
aime25_7,0.031,1,32,16384.00
aime25_8,0.031,1,32,16383.94
aime25_9,0.000,0,32,16384.00
aime25_10,0.000,0,32,16383.69
aime25_11,0.000,0,32,16384.00
aime25_12,0.000,0,32,16384.00
aime25_13,0.062,2,32,16383.97
aime25_14,0.000,0,32,16384.00
aime25_15,0.844,27,32,16384.00
aime25_16,0.250,8,32,16384.00
aime25_18,0.281,9,32,16383.88
aime25_17,0.000,0,32,16383.75
aime25_19,0.000,0,32,16384.00
aime25_20,0.031,1,32,16384.00
aime25_21,0.000,0,32,16384.00
aime25_22,0.000,0,32,16384.00
aime25_23,0.031,1,32,16384.00
aime25_24,0.000,0,32,16384.00
aime25_25,0.000,0,32,16384.00
aime25_26,0.000,0,32,16384.00
aime25_27,0.000,0,32,16383.91
aime25_28,0.031,1,32,16384.00
aime25_29,0.000,0,32,16384.34
Total Accuracy,0.145,139,960,16383.97
1 problem_id accuracy correct_count total_samples avg_output_length
2 aime25_0 0.844 27 32 16384.00
3 aime25_1 0.062 2 32 16383.78
4 aime25_2 0.688 22 32 16384.00
5 aime25_3 0.344 11 32 16384.00
6 aime25_4 0.000 0 32 16383.97
7 aime25_5 0.812 26 32 16383.97
8 aime25_6 0.000 0 32 16383.97
9 aime25_7 0.031 1 32 16384.00
10 aime25_8 0.031 1 32 16383.94
11 aime25_9 0.000 0 32 16384.00
12 aime25_10 0.000 0 32 16383.69
13 aime25_11 0.000 0 32 16384.00
14 aime25_12 0.000 0 32 16384.00
15 aime25_13 0.062 2 32 16383.97
16 aime25_14 0.000 0 32 16384.00
17 aime25_15 0.844 27 32 16384.00
18 aime25_16 0.250 8 32 16384.00
19 aime25_18 0.281 9 32 16383.88
20 aime25_17 0.000 0 32 16383.75
21 aime25_19 0.000 0 32 16384.00
22 aime25_20 0.031 1 32 16384.00
23 aime25_21 0.000 0 32 16384.00
24 aime25_22 0.000 0 32 16384.00
25 aime25_23 0.031 1 32 16384.00
26 aime25_24 0.000 0 32 16384.00
27 aime25_25 0.000 0 32 16384.00
28 aime25_26 0.000 0 32 16384.00
29 aime25_27 0.000 0 32 16383.91
30 aime25_28 0.031 1 32 16384.00
31 aime25_29 0.000 0 32 16384.34
32 Total Accuracy 0.145 139 960 16383.97

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,10226087,65.0157101949056
2,1528303,9.716688791910807
3,732614,4.657834370930989
4,3241636,20.609766642252605
Total Tokens,15728640,100.0
1 iter_count token_count percentage
2 1 10226087 65.0157101949056
3 2 1528303 9.716688791910807
4 3 732614 4.657834370930989
5 4 3241636 20.609766642252605
6 Total Tokens 15728640 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@32": 0.4667,
"cons@32": 0.2333,
"avg@32": 0.1448,
"avg_output_length": 16383.97,
"num_problems": 30,
"num_samples": 960,
"repeat_size": 32,
"avg_request_time": 325.8334,
"end_2_end_time": 2611.8533,
"token_throughtput": 6022.0123,
"request_throught": 0.3676,
"avg_iter_count": 1.8086,
"total_concurrency": 128,
"failed_requests": 0
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5780e1a7b0958b804ac6c1d7c4e04b743248d31033b8c98eeccc5e2cc8d6d0e7
size 48236268

View File

@@ -0,0 +1,961 @@
problem_id,sample_idx,correct_answer,predicted_answer,has_answer,is_correct,input_tokens,output_tokens,processing_time
aime26_1,15,277,"[277, '277']",True,True,166,16384,134.77429561095778
aime26_1,13,277,"[277, '277']",True,True,166,16384,135.70280905696563
aime26_1,31,277,"[277, '277']",True,True,166,16384,137.5812207129784
aime26_1,1,277,"[277, '277']",True,True,166,16384,140.64982309704646
aime26_1,12,277,"[277, '277']",True,True,166,16384,142.44176353001967
aime26_1,2,277,"[277, '277']",True,True,166,16384,142.46094795805402
aime26_1,20,277,"[277, '277']",True,True,166,16384,143.52319206099492
aime26_1,10,277,"[277, '277']",True,True,166,16384,143.6126011540182
aime26_1,7,277,"[277, '277']",True,True,166,16384,145.01237725489773
aime26_3,16,79,"[42, '42']",True,False,137,16384,145.38743539701682
aime26_1,25,277,"[277, '277']",True,True,166,16384,146.46217927301768
aime26_1,16,277,"[277, '277']",True,True,166,16384,147.27775920392014
aime26_1,24,277,"[277, '277']",True,True,166,16383,149.63286338292528
aime26_1,9,277,"[277, '277']",True,True,166,16384,151.64027504296973
aime26_1,18,277,"[277, '277']",True,True,166,16384,151.76163151301444
aime26_1,21,277,"[277, '277']",True,True,166,16384,155.11816306505352
aime26_1,22,277,"[277, '277']",True,True,166,16383,155.7441281210631
aime26_1,8,277,"[277, '277']",True,True,166,16384,158.9973271630006
aime26_1,29,277,"[277, '277']",True,True,166,16383,159.5448646149598
aime26_1,30,277,"[277, '277']",True,True,166,16384,165.74750621290877
aime26_1,23,277,"[277, '277']",True,True,166,16384,170.303320811945
aime26_1,19,277,"[277, '277']",True,True,166,16384,177.1560318999691
aime26_1,26,277,"[277, '277']",True,True,166,16384,177.59984589007217
aime26_1,6,277,"[277, '277']",True,True,166,16384,178.32823404797819
aime26_1,28,277,"[277, '277']",True,True,166,16382,178.4438678630395
aime26_3,5,79,"[42, '42']",True,False,137,16384,179.7478447520407
aime26_1,27,277,"[277, '277']",True,True,166,16384,180.93286803003866
aime26_2,1,62,"[5, '5']",True,False,85,16384,193.99506234005094
aime26_1,0,277,"[277, '277']",True,True,166,16384,199.12051617202815
aime26_1,3,277,"[277, '277']",True,True,166,16384,200.43822061899118
aime26_3,18,79,"[200, '200']",True,False,137,16384,201.21330349089112
aime26_3,7,79,"[42, '42']",True,False,137,16384,202.4101251210086
aime26_1,5,277,"[277, '277']",True,True,166,16384,202.68894911906682
aime26_3,22,79,"[1, '1']",True,False,137,16384,202.91442278400064
aime26_1,4,277,"[277, '277']",True,True,166,16384,210.52554363198578
aime26_3,10,79,"[1, '1']",True,False,137,16384,210.51481898198836
aime26_3,20,79,"[19559, '19559']",True,False,137,16384,212.70852139103226
aime26_2,28,62,['8 + 2 +'],True,False,85,16384,213.93810114997905
aime26_3,11,79,"[1, '1']",True,False,137,16384,215.20402541593648
aime26_3,14,79,"[1, '1']",True,False,137,16384,215.86283546697814
aime26_3,2,79,"[1, '1']",True,False,137,16384,220.69986831198912
aime26_3,8,79,"[1, '1']",True,False,137,16384,223.30379689496476
aime26_3,9,79,"[2, '2']",True,False,137,16384,225.22161486791447
aime26_1,14,277,"[277, '277']",True,True,166,16367,226.25752619595733
aime26_3,1,79,['0).'],True,False,137,16384,226.91208929906134
aime26_2,21,62,"[79, '79']",True,False,85,16384,231.91068653506227
aime26_2,13,62,"[12, '12']",True,False,85,16384,233.54165580193512
aime26_2,22,62,['15 + ..'],True,False,85,16384,236.7954011040274
aime26_1,11,277,"[277, '277']",True,True,166,16383,238.11334624898154
aime26_1,17,277,"[277, '277']",True,True,166,16383,239.68234283698257
aime26_2,7,62,"[21, '21']",True,False,85,16384,240.87529073399492
aime26_2,2,62,"[15, '15']",True,False,85,16384,243.22475534293335
aime26_3,15,79,"[79, '79']",True,True,137,16384,246.24098540702835
aime26_2,19,62,"[38, '38']",True,False,85,16384,247.4478938500397
aime26_2,24,62,"[20, '20']",True,False,85,16384,248.8499762819847
aime26_3,4,79,"[1, '1']",True,False,137,16384,251.9827228419017
aime26_2,5,62,"[15, '15']",True,False,85,16384,253.76852888101712
aime26_2,6,62,"[33, '33']",True,False,85,16384,255.56374050001614
aime26_2,17,62,"[10, '10']",True,False,85,16384,256.3175705879694
aime26_2,8,62,"[1, '1']",True,False,85,16384,257.2149356539594
aime26_3,23,79,"[71, '71']",True,False,137,16384,257.68887995695695
aime26_2,30,62,"[41, '41']",True,False,85,16384,259.19368692091666
aime26_2,10,62,"[31, '31']",True,False,85,16384,260.99050025001634
aime26_2,27,62,"[25, '25']",True,False,85,16384,261.024043885991
aime26_2,14,62,"[15, '15']",True,False,85,16384,262.24784782505594
aime26_2,11,62,"[34, '34']",True,False,85,16384,262.4699011539342
aime26_2,9,62,"[2, '2']",True,False,85,16384,263.8300104599912
aime26_3,6,79,"[84, '84']",True,False,137,16384,263.85455420194194
aime26_2,29,62,"[1, '1']",True,False,85,16384,263.9862668890273
aime26_2,16,62,"[7, '7']",True,False,85,16381,265.31413158297073
aime26_3,13,79,"[1, '1']",True,False,137,16384,266.3195504330797
aime26_2,31,62,"[20, '20']",True,False,85,16384,266.44462551397737
aime26_3,3,79,"[2, '2']",True,False,137,16384,266.60481508099474
aime26_3,17,79,"[42, '42']",True,False,137,16381,266.8133812039159
aime26_3,27,79,"[2, '2']",True,False,137,16384,267.78353567793965
aime26_2,18,62,"[1, '1']",True,False,85,16384,267.8152889449848
aime26_3,19,79,"[1, '1']",True,False,137,16384,268.01955140801147
aime26_3,25,79,['0). \n'],True,False,137,16384,268.45931235002354
aime26_3,0,79,"[200, '200']",True,False,137,16384,268.6021874679718
aime26_2,20,62,"[53, '53']",True,False,85,16384,269.1456529139541
aime26_2,26,62,"[2, '2']",True,False,85,16384,269.37000368197914
aime26_3,12,79,"[1, '1']",True,False,137,16384,269.3882264170097
aime26_2,4,62,"[5, '5']",True,False,85,16384,271.1305088130757
aime26_2,25,62,"[10, '10']",True,False,85,16384,271.80767492891755
aime26_2,3,62,"[20, '20']",True,False,85,16384,272.0920067370171
aime26_3,21,79,"[158, '158']",True,False,137,16384,273.6149851169903
aime26_2,0,62,"[13, '13']",True,False,85,16384,277.14474883896764
aime26_3,31,79,"[2, '2']",True,False,137,16384,277.20269135397393
aime26_2,15,62,"[1, '1']",True,False,85,16384,279.2785099640023
aime26_2,12,62,"[5, '5']",True,False,85,16384,281.8623461809475
aime26_3,26,79,"[24, '24']",True,False,137,16384,286.6085271689808
aime26_2,23,62,"[9, '9']",True,False,85,16384,286.6683547779685
aime26_3,30,79,"[2941, '2941']",True,False,137,16384,295.6460845649708
aime26_4,9,70,"[6, '6']",True,False,52,16384,300.2693157029571
aime26_4,7,70,"[93, '93']",True,False,52,16384,306.53644823806826
aime26_3,28,79,"[2, '2']",True,False,137,16384,307.12566971196793
aime26_3,24,79,"[42, '42']",True,False,137,16384,308.15283098700456
aime26_4,6,70,"[90, '90']",True,False,52,16384,313.9075435199775
aime26_4,15,70,"[89, '89']",True,False,52,16384,315.3880027459236
aime26_3,29,79,"[10441, '10441']",True,False,137,16384,317.344813385047
aime26_4,13,70,"[70, '70']",True,True,52,16384,339.27699473907705
aime26_4,3,70,"[25, '25']",True,False,52,16384,342.49224420497194
aime26_4,4,70,"[64, '64']",True,False,52,16384,345.90755764604546
aime26_4,0,70,"[80, '80']",True,False,52,16384,354.0466026660288
aime26_4,1,70,"[137, '137']",True,False,52,16384,356.06160642101895
aime26_4,5,70,"[4, '4']",True,False,52,16384,364.69486096606124
aime26_4,17,70,"[70, '70']",True,True,52,16384,369.4114956909325
aime26_4,19,70,"[100, '100']",True,False,52,16384,370.32856125803664
aime26_4,8,70,"[66, '66']",True,False,52,16384,371.17139041190967
aime26_5,0,65,"[65, '65']",True,True,152,16384,244.0956783130532
aime26_4,16,70,"[65, '65']",True,False,52,16384,379.1838457019767
aime26_5,4,65,"[65, '65']",True,True,152,16384,242.97654366202187
aime26_4,28,70,"[86, '86']",True,False,52,16384,386.40498800296336
aime26_4,2,70,"[22, '22']",True,False,52,16384,388.03078531997744
aime26_4,18,70,"[88, '88']",True,False,52,16384,393.68520379206166
aime26_4,11,70,"[90, '90']",True,False,52,16384,398.95809898199514
aime26_4,26,70,"[74, '74']",True,False,52,16384,399.3929473620374
aime26_4,10,70,"[71, '71']",True,False,52,16384,402.3715633730171
aime26_4,23,70,"[173, '173']",True,False,52,16384,404.6356968980981
aime26_4,21,70,"[7, '7']",True,False,52,16384,405.4388154600747
aime26_4,12,70,"[137, '137']",True,False,52,16384,407.3292882019887
aime26_6,11,441,"[80, '80']",True,False,68,16384,184.09987885691226
aime26_5,10,65,"[65, '65']",True,True,152,16384,271.7769234320149
aime26_4,27,70,"[89, '89']",True,False,52,16384,418.9449963020161
aime26_4,14,70,"[65, '65']",True,False,52,16384,422.27992245706264
aime26_4,29,70,"[70, '70']",True,True,52,16384,427.2406752840616
aime26_4,30,70,"[71, '71']",True,False,52,16384,428.3074553500628
aime26_5,8,65,"[65, '65']",True,True,152,16384,284.08525902905967
aime26_5,19,65,"[65, '65']",True,True,152,16384,267.3711293839151
aime26_5,2,65,"[65, '65']",True,True,152,16384,295.6914254829753
aime26_5,16,65,"[65, '65']",True,True,152,16384,281.2947311960161
aime26_5,23,65,"[65, '65']",True,True,152,16384,259.54872516193427
aime26_5,7,65,"[29/36.0, '29/36.']",True,False,152,16384,295.23566888505593
aime26_4,31,70,"[137, '137']",True,False,52,16384,445.6308536210563
aime26_5,11,65,"[65, '65']",True,True,152,16384,298.80851617397275
aime26_4,25,70,"[7, '7']",True,False,52,16384,449.8943001149455
aime26_5,29,65,"[65, '65']",True,True,152,16384,250.0648035829654
aime26_5,18,65,"[65, '65']",True,True,152,16384,291.0090890380088
aime26_5,1,65,"[65, '65']",True,True,152,16384,314.9012257499853
aime26_4,24,70,"[137, '137']",True,False,52,16384,455.37425539200194
aime26_4,22,70,"[137, '137']",True,False,52,16384,457.00957956002094
aime26_5,5,65,['1).'],True,False,152,16384,316.60183208889794
aime26_5,9,65,['1).'],True,False,152,16384,315.48646077606827
aime26_5,22,65,"[65, '65']",True,True,152,16384,286.92756386403926
aime26_4,20,70,"[75, '75']",True,False,52,16384,465.49895110109355
aime26_5,14,65,"[4, '4']",True,False,152,16384,318.85154722305015
aime26_5,31,65,"[65, '65']",True,True,152,16384,273.8667798630195
aime26_5,20,65,"[65, '65']",True,True,152,16384,309.81952702300623
aime26_6,2,441,"[441, '441']",True,True,68,16384,270.2245807880536
aime26_6,12,441,"[441, '441']",True,True,68,16384,258.71722224901896
aime26_5,27,65,"[44, '44']",True,False,152,16384,292.25113211700227
aime26_5,6,65,"[5, '5']",True,False,152,16384,343.1885427159723
aime26_6,5,441,"[4, '4']",True,False,68,16384,276.09153428603895
aime26_5,25,65,"[-1*0.033 - 1*0 + 0.343, '0.343 - 0.0330 - 0']",True,False,152,16384,311.8192951969104
aime26_5,3,65,"[65, '65']",True,True,152,16384,351.66651753301267
aime26_5,26,65,"[6, '6']",True,False,152,16384,311.70235578506254
aime26_5,17,65,"[65, '65']",True,True,152,16383,334.817371246987
aime26_5,21,65,"[0, '0']",True,False,152,16384,317.9936677310616
aime26_6,0,441,"[4, '4']",True,False,68,16384,292.54528923204634
aime26_6,18,441,"[441, '441']",True,True,68,16384,257.47149496199563
aime26_5,12,65,['(1 - 2'],True,False,152,16384,353.0499069900252
aime26_6,1,441,"[441, '441']",True,True,68,16384,301.41181612899527
aime26_6,29,441,"[441, '441']",True,True,68,16384,246.06771693995688
aime26_5,15,65,"[65, '65']",True,True,152,16384,350.5156113059493
aime26_5,13,65,"[90, '90']",True,False,152,16384,354.67130293895025
aime26_6,19,441,"[200, '200']",True,False,68,16384,268.46950695302803
aime26_6,15,441,"[441, '441']",True,True,68,16384,274.9611272600014
aime26_6,9,441,"[26, '26']",True,False,68,16384,288.65659015998244
aime26_6,7,441,"[26, '26']",True,False,68,16384,297.4955001079943
aime26_6,3,441,"[-0.400000000000000, '-0.4']",True,False,68,16384,304.8267116150819
aime26_6,8,441,"[26, '26']",True,False,68,16384,295.7286849679658
aime26_6,10,441,"[26, '26']",True,False,68,16384,292.8044942080742
aime26_6,17,441,"[16, '16']",True,False,68,16384,279.9178612360265
aime26_6,6,441,"[441, '441']",True,True,68,16384,304.5307096239412
aime26_6,27,441,"[441, '441']",True,True,68,16384,264.35084101196844
aime26_5,30,65,"[65, '65']",True,True,152,16384,321.6101568969898
aime26_6,14,441,"[441, '441']",True,True,68,16384,289.6423368930118
aime26_6,30,441,"[441, '441']",True,True,68,16384,262.75079676602036
aime26_6,22,441,"[2, '2']",True,False,68,16384,275.2806919880677
aime26_6,4,441,"[441, '441']",True,True,68,16384,311.8565369140124
aime26_6,16,441,"[18081, '18081']",True,False,68,16384,286.97725864103995
aime26_6,20,441,"[1, '1']",True,False,68,16384,282.4508435910102
aime26_7,3,396,"[145, '145']",True,False,83,16384,265.0680449119536
aime26_6,31,441,"[1/20, '1 / 20']",True,False,68,16384,269.33968355692923
aime26_6,21,441,"[2026, '2026']",True,False,68,16384,283.8166032480076
aime26_6,13,441,"[26, '26']",True,False,68,16384,301.3187062960351
aime26_7,7,396,"[145, '145']",True,False,83,16384,267.2090685790172
aime26_7,4,396,"[1, '1']",True,False,83,16384,270.0965168320108
aime26_7,21,396,"[6, '6']",True,False,83,16384,261.23715727205854
aime26_5,24,65,['0).'],True,False,152,16384,357.5881059949752
aime26_6,23,441,"[441, '441']",True,True,68,16384,285.3934911999386
aime26_6,26,441,"[26, '26']",True,False,68,16384,281.25765663490165
aime26_5,28,65,"[16/9.0, '16/9.']",True,False,152,16384,338.9146829160163
aime26_6,24,441,"[441, '441']",True,True,68,16384,285.4074419440003
aime26_6,28,441,"[20.4200000000000, '20.42']",True,False,68,16384,285.37431196693797
aime26_7,6,396,"[144, '144']",True,False,83,16384,279.71426997403614
aime26_6,25,441,"[441, '441']",True,True,68,16384,291.8047097789822
aime26_7,1,396,"[176, '176']",True,False,83,16384,285.76536077295896
aime26_7,2,396,"[145, '145']",True,False,83,16384,290.1915022949688
aime26_7,19,396,"[144, '144']",True,False,83,16384,284.8910701900022
aime26_7,23,396,"[144, '144']",True,False,83,16384,281.5582423929591
aime26_7,11,396,"[1, '1']",True,False,83,16384,298.63355440902524
aime26_7,27,396,"[1, '1']",True,False,83,16384,289.84708561503794
aime26_7,26,396,"[144, '144']",True,False,83,16384,302.87250807799865
aime26_7,22,396,"[1, '1']",True,False,83,16384,312.49028898600955
aime26_7,8,396,"[144, '144']",True,False,83,16384,329.642205556971
aime26_8,2,244,"[244, '244']",True,True,72,16384,297.256799660041
aime26_7,24,396,"[145, '145']",True,False,83,16384,341.3571004800033
aime26_7,20,396,"[144, '144']",True,False,83,16384,348.9899097359739
aime26_7,14,396,"[145, '145']",True,False,83,16384,352.4944593970431
aime26_7,9,396,"[120, '120']",True,False,83,16384,354.99406649102457
aime26_7,15,396,"[2, '2']",True,False,83,16384,356.4706223240355
aime26_7,0,396,"[289, '289']",True,False,83,16384,369.6006611729972
aime26_8,10,244,"[244, '244']",True,True,72,16384,263.29919046803843
aime26_7,13,396,"[144, '144']",True,False,83,16384,371.6238659910159
aime26_9,6,29,"[6, '6']",True,False,192,16384,198.31673118995968
aime26_9,11,29,"[6, '6']",True,False,192,16384,191.23512401198968
aime26_7,16,396,"[720, '720']",True,False,83,16384,379.7711994389538
aime26_7,12,396,"[144, '144']",True,False,83,16384,383.3182889439631
aime26_9,4,29,"[2, '2']",True,False,192,16384,216.66299774695653
aime26_7,5,396,"[288, '288']",True,False,83,16384,390.3024701549439
aime26_7,31,396,"[145, '145']",True,False,83,16384,352.66573005297687
aime26_9,3,29,"[4, '4']",True,False,192,16384,223.04878987499978
aime26_8,11,244,"[0, '0']",True,False,72,16384,291.25984998000786
aime26_7,25,396,"[145, '145']",True,False,83,16384,380.7551164450124
aime26_7,29,396,"[1, '1']",True,False,83,16384,364.89851499104407
aime26_9,5,29,"[2, '2']",True,False,192,16384,221.63837249204516
aime26_9,2,29,"[3, '3']",True,False,192,16384,231.5467264619656
aime26_8,0,244,"[916, '916']",True,False,72,16384,361.2043145070784
aime26_9,7,29,"[2, '2']",True,False,192,16384,221.6332370940363
aime26_9,21,29,"[6, '6']",True,False,192,16384,186.7255224030232
aime26_9,23,29,"[6, '6']",True,False,192,16384,189.6964667410357
aime26_8,4,244,"[810, '810']",True,False,72,16384,339.37614776496775
aime26_8,25,244,"[0, '0']",True,False,72,16384,269.86384164495394
aime26_8,23,244,"[9, '9']",True,False,72,16384,277.6189189259894
aime26_9,18,29,"[2, '2']",True,False,192,16384,206.9695194249507
aime26_8,3,244,"[244, '244']",True,True,72,16384,370.1650946880691
aime26_7,17,396,"[186, '186']",True,False,83,16384,418.8567254350055
aime26_8,28,244,"[916, '916']",True,False,72,16384,266.43057597090956
aime26_8,5,244,"[392, '392']",True,False,72,16384,346.8135666429298
aime26_9,14,29,"[1, '1']",True,False,192,16384,229.950331059983
aime26_9,8,29,"[2, '2']",True,False,192,16384,241.84489837498404
aime26_7,10,396,"[265, '265']",True,False,83,16384,424.9000539970584
aime26_8,15,244,"[288, '288']",True,False,72,16384,308.46706134302076
aime26_9,9,29,"[2, '2']",True,False,192,16384,243.9275676680263
aime26_7,18,396,"[175, '175']",True,False,83,16384,430.88447471300606
aime26_8,7,244,"[1296, '1296']",True,False,72,16384,348.1019606780028
aime26_8,8,244,"[392, '392']",True,False,72,16384,346.29379061597865
aime26_9,30,29,"[2, '2']",True,False,192,16384,209.28173514502123
aime26_7,28,396,"[144, '144']",True,False,83,16384,409.2050212790491
aime26_9,15,29,"[3, '3']",True,False,192,16384,240.6167516990099
aime26_9,26,29,"[6, '6']",True,False,192,16384,213.8559017139487
aime26_9,22,29,"[2, '2']",True,False,192,16384,221.51579072605819
aime26_8,6,244,"[12, '12']",True,False,72,16384,363.6257795689162
aime26_8,19,244,"[2, '2']",True,False,72,16384,310.9007001189748
aime26_9,17,29,"[2, '2']",True,False,192,16384,240.85382933006622
aime26_9,29,29,"[6, '6']",True,False,192,16384,217.73675071401522
aime26_7,30,396,"[144, '144']",True,False,83,16384,406.54220191796776
aime26_9,12,29,"[2, '2']",True,False,192,16384,257.343769179075
aime26_8,1,244,"[832, '832']",True,False,72,16384,401.1092713329708
aime26_8,12,244,"[81, '81']",True,False,72,16384,347.0412950719474
aime26_9,13,29,"[3, '3']",True,False,192,16384,259.76377470896114
aime26_8,22,244,"[0, '0']",True,False,72,16384,319.37727880396415
aime26_8,13,244,"[916, '916']",True,False,72,16384,350.36329651996493
aime26_9,20,29,"[6, '6']",True,False,192,16384,248.5885623630602
aime26_9,31,29,"[6, '6']",True,False,192,16384,231.01300975703634
aime26_8,30,244,"[162, '162']",True,False,72,16384,302.8673607399687
aime26_10,15,156,"[90, '90']",True,False,120,16384,208.55256121209823
aime26_8,16,244,"[162, '162']",True,False,72,16384,345.39930093090516
aime26_8,27,244,"[458, '458']",True,False,72,16384,313.8198327800492
aime26_8,20,244,"[160, '160']",True,False,72,16384,335.0499245818937
aime26_8,21,244,"[244, '244']",True,True,72,16384,332.6422999060014
aime26_8,26,244,"[458, '458']",True,False,72,16384,319.3869919740828
aime26_9,0,29,"[6, '6']",True,False,192,16384,306.09978171100374
aime26_8,31,244,"[992, '992']",True,False,72,16384,310.6315540210344
aime26_8,9,244,"[0, '0']",True,False,72,16384,375.2215174839366
aime26_8,18,244,"[103, '103']",True,False,72,16384,352.0987747410545
aime26_9,19,29,"[5/2187.0, '5 / 2187. \n']",True,False,192,16384,267.90877125097904
aime26_8,29,244,"[488, '488']",True,False,72,16384,322.20636943995487
aime26_9,16,29,"[1, '1']",True,False,192,16384,288.81408902909607
aime26_9,10,29,"[6, '6']",True,False,192,16384,304.0382817189675
aime26_9,1,29,"[2, '2']",True,False,192,16384,327.5026161270216
aime26_9,28,29,"[2, '2']",True,False,192,16384,270.12404160993174
aime26_8,17,244,"[162, '162']",True,False,72,16384,377.37112374196295
aime26_8,14,244,"[244, '244']",True,True,72,16384,386.4450833259616
aime26_9,27,29,"[3, '3']",True,False,192,16384,273.29587970103603
aime26_10,18,156,"[4, '4']",True,False,120,16384,246.10771127103362
aime26_9,25,29,"[6, '6']",True,False,192,16384,288.2122847089777
aime26_10,2,156,"[135, '135']",True,False,120,16384,280.267433178029
aime26_8,24,244,"[1, '1']",True,False,72,16384,381.5664451010525
aime26_10,11,156,"[-23, '-23']",True,False,120,16384,276.411418036907
aime26_10,13,156,"[14, '14']",True,False,120,16384,275.2011213309597
aime26_10,3,156,"[603/40, '603/40']",True,False,120,16384,299.76440358092077
aime26_10,7,156,['1.4 + '],True,False,120,16384,295.7335444689961
aime26_9,24,29,"[1, '1']",True,False,192,16384,319.37895233300515
aime26_10,31,156,"[90, '90']",True,False,120,16384,271.9019882749999
aime26_10,5,156,['89/8). \n'],True,False,120,16384,298.1490148539888
aime26_10,6,156,"[-1, '-1']",True,False,120,16383,308.1066521749599
aime26_11,7,896,"[1, '1']",True,False,172,16384,268.1387032730272
aime26_10,0,156,['(35/2)(-'],True,False,120,16384,322.3596027479507
aime26_10,4,156,['(-9)(3/5) + (15/4)(4/5) + 33/8\n\n'],True,False,120,16384,319.7129112279508
aime26_10,19,156,"[1089, '1089']",True,False,120,16384,304.2258708620211
aime26_11,3,896,"[64 - 1*6, '64 - 6']",True,False,172,16384,288.7387018529698
aime26_10,10,156,['-4225*56 - 4225*'],True,False,120,16384,325.4656512719812
aime26_10,12,156,"[160, '160']",True,False,120,16384,325.9069039740134
aime26_10,17,156,"[-7/3.0, '-7/3.\n']",True,False,120,16384,323.63646447099745
aime26_10,14,156,"[-56/33.0, '-56/33. \n']",True,False,120,16384,333.3260841059964
aime26_12,7,161,"[2, '2']",True,False,196,16384,178.93453455297276
aime26_10,21,156,"[521, '521']",True,False,120,16384,328.7404847739963
aime26_11,12,896,"[1, '1']",True,False,172,16384,269.60579137702007
aime26_10,27,156,['-33/8).\n'],True,False,120,16384,327.92567154194694
aime26_10,23,156,['33/8).'],True,False,120,16384,339.3038604820613
aime26_11,28,896,"[56, '56']",True,False,172,16384,215.54940424393862
aime26_10,1,156,"[5.02500000000000, '5.025']",True,False,120,16384,370.2253220070852
aime26_11,18,896,"[7, '7']",True,False,172,16384,253.879476854112
aime26_11,15,896,"[0, '0']",True,False,172,16384,256.2835035499884
aime26_10,22,156,"[90, '90']",True,False,120,16384,348.5618194519775
aime26_11,29,896,"[64, '64']",True,False,172,16384,220.5628901369637
aime26_11,14,896,"[63, '63']",True,False,172,16384,269.4031818700023
aime26_11,22,896,"[2, '2']",True,False,172,16384,245.50000791996717
aime26_10,9,156,['0.8).'],True,False,120,16383,374.67650265898556
aime26_10,20,156,['33/8).'],True,False,120,16384,365.8481827030191
aime26_11,5,896,['(3). (1)'],True,False,172,16384,346.03782451094594
aime26_10,26,156,"[0, '0']",True,False,120,16384,362.5769248730503
aime26_10,8,156,"[1/2, '1/2']",True,False,120,16384,387.6053151950473
aime26_10,28,156,"[13.8750000000000, '13.875']",True,False,120,16384,369.6759151640581
aime26_11,13,896,"[1, '1']",True,False,172,16384,316.06280291092116
aime26_10,30,156,"[156, '156']",True,True,120,16384,375.81433411396574
aime26_10,29,156,"[1521/1531.0, '1521/1531.']",True,False,120,16384,381.1568872999633
aime26_11,11,896,"[64, '64']",True,False,172,16384,338.44366289197933
aime26_10,16,156,"[12, '12']",True,False,120,16384,405.3018175640609
aime26_10,25,156,['33/(1'],True,False,120,16384,398.5649297890486
aime26_11,2,896,"[6, '6']",True,False,172,16384,389.0639778659679
aime26_10,24,156,"[12, '12']",True,False,120,16384,402.2364356010221
aime26_11,10,896,"[64, '64']",True,False,172,16384,374.77945253497455
aime26_11,1,896,"[4, '4']",True,False,172,16384,417.2937054251088
aime26_11,8,896,"[63, '63']",True,False,172,16384,398.7829933320172
aime26_12,5,161,"[2, '2']",True,False,196,16384,286.27793643891346
aime26_11,6,896,"[63, '63']",True,False,172,16384,405.26738215307705
aime26_11,27,896,"[256, '256']",True,False,172,16384,308.50421167106833
aime26_11,23,896,"[10, '10']",True,False,172,16384,319.76813179510646
aime26_11,4,896,"[7, '7']",True,False,172,16384,417.4820209930185
aime26_12,4,161,"[0, '0']",True,False,196,16384,296.7784244400682
aime26_12,15,161,"[44/1, '44/1']",True,False,196,16384,288.8533034280408
aime26_11,0,896,"[1, '1']",True,False,172,16384,440.25967135303654
aime26_11,31,896,"[63, '63']",True,False,172,16384,316.6869206869742
aime26_12,10,161,"[8, '8']",True,False,196,16384,297.4066598250065
aime26_12,23,161,"[4, '4']",True,False,196,16384,282.4203065530164
aime26_11,19,896,"[8, '8']",True,False,172,16384,363.7781490900088
aime26_12,31,161,"[1, '1']",True,False,196,16384,278.65476883901283
aime26_12,3,161,"[4, '4']",True,False,196,16384,321.7746555809863
aime26_11,20,896,"[252, '252']",True,False,172,16384,358.92994763096794
aime26_11,16,896,"[5760, '5760']",True,False,172,16384,371.70736664696597
aime26_12,12,161,"[3, '3']",True,False,196,16384,309.07561751792673
aime26_13,15,39,"[502, '502']",True,False,190,16384,265.7713951750193
aime26_12,14,161,"[0, '0']",True,False,196,16384,313.4196494369535
aime26_13,7,39,"[0, '0']",True,False,190,16384,275.6535160141066
aime26_12,2,161,"[6, '6']",True,False,196,16384,339.60977226810064
aime26_12,6,161,"[62, '62']",True,False,196,16383,339.23010652908124
aime26_11,25,896,"[8, '8']",True,False,172,16384,364.8820165611105
aime26_12,21,161,"[-16/13, '-16/13']",True,False,196,16384,312.1724656189326
aime26_12,11,161,"[4, '4']",True,False,196,16384,331.5131335289916
aime26_12,8,161,"[42/13, '42/13']",True,False,196,16384,336.217902706936
aime26_12,13,161,"[0.000434400000000000, '0.0004344']",True,False,196,16384,328.7295371640939
aime26_13,11,39,['(1/502) * 10000 *'],True,False,190,16384,287.4105643519433
aime26_11,9,896,"[1, '1']",True,False,172,16384,453.4145278109936
aime26_11,21,896,"[-1, '-1']",True,False,172,16384,392.2047894130228
aime26_12,17,161,"[0.933000000000000, '0.933']",True,False,196,16384,334.5775631070137
aime26_12,26,161,"[2, '2']",True,False,196,16384,322.79107444395777
aime26_13,2,39,"[2, '2']",True,False,190,16384,314.2715831800597
aime26_12,20,161,"[3, '3']",True,False,196,16384,336.3852410999825
aime26_11,26,896,"[196/2, '196 / 2']",True,False,172,16381,379.83791958296206
aime26_12,1,161,['124/39 +'],True,False,196,16384,366.19521892094053
aime26_12,18,161,['0).'],True,False,196,16384,340.49405911308713
aime26_12,29,161,"[3, '3']",True,False,196,16384,324.73138904804364
aime26_12,16,161,['(34/1'],True,False,196,16384,346.1644895209465
aime26_11,24,896,"[2, '2']",True,False,172,16384,391.4470455229748
aime26_11,17,896,"[64, '64']",True,False,172,16384,417.07063584495336
aime26_12,19,161,"[3, '3']",True,False,196,16384,345.8206261449959
aime26_13,3,39,"[503, '503']",True,False,190,16384,326.96142328798305
aime26_12,0,161,"[39, '39']",True,False,196,16384,380.6939633570146
aime26_12,30,161,"[0, '0']",True,False,196,16384,334.64006177301053
aime26_13,23,39,"[0, '0']",True,False,190,16384,294.0929686889285
aime26_13,21,39,"[0, '0']",True,False,190,16384,302.88382985198405
aime26_13,4,39,"[0, '0']",True,False,190,16384,336.92840648896527
aime26_12,27,161,"[0, '0']",True,False,196,16384,356.4503721470246
aime26_13,5,39,"[0, '0']",True,False,190,16384,343.84724998800084
aime26_11,30,896,"[8, '8']",True,False,172,16384,403.819061758928
aime26_12,9,161,"[0, '0']",True,False,196,16384,388.4950877999654
aime26_13,6,39,"[502, '502']",True,False,190,16384,346.319295070949
aime26_13,18,39,"[1, '1']",True,False,190,16384,336.68054211197887
aime26_13,12,39,"[0, '0']",True,False,190,16384,349.18500210298225
aime26_13,10,39,"[0, '0']",True,False,190,16384,349.97793437191285
aime26_12,28,161,"[117, '117']",True,False,196,16384,374.25811822200194
aime26_12,22,161,"[0, '0']",True,False,196,16384,380.6374352009734
aime26_12,25,161,"[156, '156']",True,False,196,16384,378.68654671194963
aime26_13,31,39,"[0, '0']",True,False,190,16384,304.9473666999256
aime26_12,24,161,"[0, '0']",True,False,196,16384,380.6604241040768
aime26_13,0,39,"[0, '0']",True,False,190,16384,372.3395297219977
aime26_14,14,681,"[1, '1']",True,False,107,16384,259.23285224905703
aime26_13,13,39,"[503, '503']",True,False,190,16384,362.75423265399877
aime26_13,27,39,"[40, '40']",True,False,190,16384,340.6071197279962
aime26_13,17,39,"[1, '1']",True,False,190,16384,368.7414992569247
aime26_14,21,681,"[1, '1']",True,False,107,16384,249.5323887130944
aime26_13,1,39,"[0, '0']",True,False,190,16384,398.62394552805927
aime26_13,19,39,"[0, '0']",True,False,190,16384,372.0222592500504
aime26_14,7,681,"[308, '308']",True,False,107,16383,304.26282147003803
aime26_13,14,39,"[2, '2']",True,False,190,16384,380.53606919304
aime26_14,12,681,"[3, '3']",True,False,107,16384,289.0577373689739
aime26_13,20,39,"[0, '0']",True,False,190,16384,375.7042971950723
aime26_13,8,39,"[11, '11']",True,False,190,16383,394.60590776696336
aime26_13,26,39,"[58, '58']",True,False,190,16384,361.9241863399511
aime26_13,29,39,"[9766, '9766']",True,False,190,16384,366.7879649749957
aime26_13,9,39,"[503, '503']",True,False,190,16384,403.64599277998786
aime26_14,19,681,"[1, '1']",True,False,107,16384,288.71703306399286
aime26_14,5,681,"[1/2, '1/2']",True,False,107,16384,340.66435339697637
aime26_13,28,39,"[0, '0']",True,False,190,16384,386.0049958860036
aime26_13,22,39,"[5, '5']",True,False,190,16384,403.3914430590812
aime26_14,29,681,"[3, '3']",True,False,107,16384,281.38201325794216
aime26_14,11,681,"[2, '2']",True,False,107,16384,339.09332119009923
aime26_13,30,39,"[502, '502']",True,False,190,16384,396.7957950759446
aime26_14,15,681,"[400, '400']",True,False,107,16384,326.3138860450126
aime26_14,3,681,"[1540, '1540']",True,False,107,16384,376.18477640103083
aime26_14,23,681,"[2, '2']",True,False,107,16384,303.2593154379865
aime26_14,22,681,"[2, '2']",True,False,107,16384,315.79268273699563
aime26_14,6,681,"[2, '2']",True,False,107,16384,374.1686203009449
aime26_14,4,681,"[2.61800000000000, '2.618']",True,False,107,16384,386.6405701749027
aime26_14,26,681,['1)/'],True,False,107,16384,323.2896898930194
aime26_14,10,681,"[-290, '-290']",True,False,107,16384,377.70615759899374
aime26_14,13,681,"[72, '72']",True,False,107,16384,373.94181904301513
aime26_15,23,83,"[2, '2']",True,False,265,16384,233.23109149199445
aime26_13,25,39,"[501, '501']",True,False,190,16384,456.6857058129972
aime26_13,16,39,"[1, '1']",True,False,190,16384,481.9078028360382
aime26_13,24,39,"[0, '0']",True,False,190,16384,466.775175562012
aime26_14,18,681,"[308, '308']",True,False,107,16384,367.90115797903854
aime26_14,0,681,"[0, '-0']",True,False,107,16384,444.30647348205093
aime26_14,2,681,"[2, '2']",True,False,107,16384,436.8336673909798
aime26_14,30,681,"[4, '4']",True,False,107,16384,349.44176964391954
aime26_14,1,681,"[5, '5']",True,False,107,16384,444.66639669588767
aime26_16,23,178,"[178, '178']",True,True,58,16384,205.62018690700643
aime26_14,8,681,['1)/4 * 2'],True,False,107,16384,436.8957840380026
aime26_16,2,178,"[178, '178']",True,True,58,16384,247.3203694249969
aime26_14,20,681,"[800, '800']",True,False,107,16384,391.33323896001093
aime26_15,13,83,"[5, '5']",True,False,265,16384,315.4672626539832
aime26_16,15,178,"[178, '178']",True,True,58,16384,222.4876748219831
aime26_14,31,681,['2-4). \n'],True,False,107,16383,364.06184034398757
aime26_15,7,83,"[5, '5']",True,False,265,16384,336.5160237309756
aime26_16,7,178,"[178, '178']",True,True,58,16384,236.30408048001118
aime26_14,17,681,"[800, '800']",True,False,107,16384,404.13785703200847
aime26_16,3,178,"[178, '178']",True,True,58,16384,252.0510226849001
aime26_14,27,681,"[2, '2']",True,False,107,16384,377.5783157279948
aime26_14,16,681,"[-184, '-184']",True,False,107,16384,413.71698021900374
aime26_15,28,83,"[12, '12']",True,False,265,16384,273.2774544240674
aime26_16,13,178,"[178, '178']",True,True,58,16384,242.87935466703493
aime26_16,31,178,"[178, '178']",True,True,58,16384,214.3180837359978
aime26_16,4,178,"[178, '178']",True,True,58,16384,263.27735008404125
aime26_14,28,681,"[2, '2']",True,False,107,16384,394.97043026890606
aime26_15,26,83,"[10, '10']",True,False,265,16384,292.81422881700564
aime26_15,5,83,"[2, '2']",True,False,265,16384,370.3800397469895
aime26_16,10,178,"[178, '178']",True,True,58,16384,266.1407008350361
aime26_15,15,83,"[5, '5']",True,False,265,16384,325.75354475108907
aime26_16,0,178,"[178, '178']",True,True,58,16384,294.52419706701767
aime26_14,9,681,"[2, '2']",True,False,107,16384,469.6250059240265
aime26_14,24,681,"[108, '108']",True,False,107,16384,418.3549683870515
aime26_17,7,243,"[10, '10']",True,False,369,16384,209.10605586494785
aime26_16,18,178,"[178, '178']",True,True,58,16384,260.63941483199596
aime26_15,2,83,"[21, '21']",True,False,265,16384,401.83065118792
aime26_16,19,178,"[178, '178']",True,True,58,16384,267.7884453299921
aime26_15,6,83,"[2, '2']",True,False,265,16384,388.08377294708043
aime26_17,5,243,"[1, '1']",True,False,369,16384,232.70200040598866
aime26_16,20,178,"[178, '178']",True,True,58,16384,271.8096692559775
aime26_16,26,178,"[178, '178']",True,True,58,16384,264.59788184496574
aime26_15,3,83,"[1, '1']",True,False,265,16384,408.6881536919391
aime26_16,12,178,"[178, '178']",True,True,58,16384,287.00025533302687
aime26_15,31,83,"[10, '10']",True,False,265,16384,316.8658384840237
aime26_16,14,178,"[178, '178']",True,True,58,16384,283.21151920000557
aime26_16,9,178,"[-2, '-2']",True,False,58,16384,293.5685303249629
aime26_16,5,178,"[24, '24']",True,False,58,16384,303.27532372495625
aime26_15,12,83,"[5, '5']",True,False,265,16388,379.5600662960205
aime26_16,6,178,"[178, '178']",True,True,58,16384,301.0462891180068
aime26_15,22,83,"[5, '5']",True,False,265,16384,346.7132376029622
aime26_15,10,83,"[120, '120']",True,False,265,16384,384.6827885339735
aime26_16,21,178,"[178, '178']",True,True,58,16384,280.4042428539833
aime26_14,25,681,"[2, '2']",True,False,107,16384,446.1858595380327
aime26_15,20,83,"[21, '21']",True,False,265,16384,358.0112816769397
aime26_15,4,83,"[2, '2']",True,False,265,16384,423.0209839390591
aime26_16,27,178,"[178, '178']",True,True,58,16384,282.144441050943
aime26_15,14,83,"[2, '2']",True,False,265,16384,377.8026919440599
aime26_15,21,83,"[5, '5']",True,False,265,16384,365.6220587049611
aime26_16,29,178,"[178, '178']",True,True,58,16384,289.04695653996896
aime26_16,11,178,"[165, '165']",True,False,58,16384,317.08520313201007
aime26_15,29,83,"[5, '5']",True,False,265,16384,347.39833492506295
aime26_15,19,83,"[1, '1']",True,False,265,16384,374.4522898889845
aime26_15,18,83,"[5, '5']",True,False,265,16384,382.6047315290198
aime26_16,8,178,"[178, '178']",True,True,58,16384,329.38757130294107
aime26_15,11,83,"[12, '12']",True,False,265,16384,411.8613644379657
aime26_16,30,178,"[178, '178']",True,True,58,16384,295.6823500250466
aime26_16,28,178,"[178, '178']",True,True,58,16384,300.8178362289909
aime26_16,16,178,"[32, '32']",True,False,58,16384,318.7794563550269
aime26_17,31,243,['0).'],True,False,369,16384,204.90040430100635
aime26_16,17,178,"[178, '178']",True,True,58,16384,325.12364382704254
aime26_15,0,83,"[5, '5']",True,False,265,16384,463.8715728119714
aime26_15,9,83,"[2, '2']",True,False,265,16384,429.1758108129725
aime26_15,8,83,"[1, '1']",True,False,265,16384,444.3228299950715
aime26_15,30,83,"[100, '100']",True,False,265,16384,372.06599287095014
aime26_15,27,83,"[4, '4']",True,False,265,16384,379.9468840090558
aime26_15,1,83,"[126, '126']",True,False,265,16384,475.7266066179145
aime26_16,22,178,"[178, '178']",True,True,58,16384,335.24523014295846
aime26_15,16,83,"[6, '6']",True,False,265,16384,412.6573353239801
aime26_17,26,243,"[1, '1']",True,False,369,16384,248.2532445479883
aime26_17,23,243,"[10, '10']",True,False,369,16384,260.9219120760681
aime26_16,1,178,"[178, '178']",True,True,58,16384,380.9064975139918
aime26_15,17,83,"[4, '4']",True,False,265,16384,422.233889504103
aime26_17,3,243,"[1, '1']",True,False,369,16384,315.5343959949678
aime26_15,25,83,"[1, '1']",True,False,265,16384,410.5522578150267
aime26_17,27,243,"[10, '10']",True,False,369,16384,265.9303741049953
aime26_15,24,83,"[10, '10']",True,False,265,16384,414.30071893602144
aime26_17,1,243,"[1, '1']",True,False,369,16384,331.1239894530736
aime26_17,13,243,"[362880, '362880']",True,False,369,16384,332.30457129806746
aime26_16,25,178,"[178, '178']",True,True,58,16384,379.59483606694266
aime26_17,22,243,"[sqrt(11), '\\sqrt{11}']",True,False,369,16384,308.86588410299737
aime26_17,18,243,"[9, '9']",True,False,369,16384,316.05851335602347
aime26_17,24,243,"[10, '10']",True,False,369,16384,316.29409562807996
aime26_17,15,243,"[2, '2']",True,False,369,16384,337.76417696790304
aime26_18,10,503,"[0, '0']",True,False,150,16384,245.30731063499115
aime26_17,4,243,"[10, '10']",True,False,369,16384,369.9160043710144
aime26_18,31,503,"[45, '45']",True,False,150,16384,190.59555449697655
aime26_17,11,243,"[2, '2']",True,False,369,16384,358.6783873740351
aime26_17,6,243,"[11, '11']",True,False,369,16384,373.0730599020608
aime26_17,19,243,"[10, '10']",True,False,369,16384,340.7387321740389
aime26_17,2,243,"[430, '430']",True,False,369,16384,390.6090245679952
aime26_17,21,243,"[1, '1']",True,False,369,16384,344.8900457409909
aime26_16,24,178,"[178, '178']",True,True,58,16384,441.1594640830299
aime26_17,14,243,"[0, '0']",True,False,369,16384,394.21008377696853
aime26_18,7,503,"[126, '126']",True,False,150,16384,310.2969554460142
aime26_17,10,243,"[2, '2']",True,False,369,16384,413.8905827529961
aime26_19,2,279,"[2, '2']",True,False,143,16384,245.4408885409357
aime26_18,15,503,"[2022, '2022']",True,False,150,16384,284.9995242799632
aime26_17,29,243,"[11, '11']",True,False,369,16384,371.1116032419959
aime26_17,9,243,"[sqrt(11), '\\sqrt{11}']",True,False,369,16384,429.4266384630464
aime26_18,5,503,"[10, '10']",True,False,150,16384,343.7767961079953
aime26_17,0,243,"[10, '10']",True,False,369,16384,460.6853696509497
aime26_17,17,243,"[1, '1']",True,False,369,16384,410.3506849500118
aime26_18,2,503,"[1, '1']",True,False,150,16384,355.316159440903
aime26_19,15,279,"[58, '58']",True,False,143,16384,230.16082769806962
aime26_20,2,190,"[2, '2']",True,False,105,16385,206.26670655200724
aime26_17,8,243,['1). \n'],True,False,369,16384,445.0477843990084
aime26_17,12,243,"[11, '11']",True,False,369,16384,444.8906507890206
aime26_17,20,243,"[sqrt(10), '\\sqrt{10}']",True,False,369,16384,421.06428736797534
aime26_18,4,503,"[28, '28']",True,False,150,16384,369.09983424306847
aime26_18,3,503,"[1, '1']",True,False,150,16384,373.1530039400095
aime26_18,23,503,"[45, '45']",True,False,150,16384,295.64824117789976
aime26_17,30,243,"[11, '11']",True,False,369,16384,396.90061193401925
aime26_18,13,503,"[128*19, '128*(19)']",True,False,150,16384,338.1938798810588
aime26_19,7,279,"[7, '7']",True,False,143,16384,277.6934892440913
aime26_18,6,503,"[2, '2']",True,False,150,16384,375.09152839693706
aime26_18,18,503,['20)^2'],True,False,150,16384,323.6613525720313
aime26_19,10,279,"[9, '9']",True,False,143,16384,277.215089141042
aime26_18,11,503,"[1009, '1009']",True,False,150,16384,353.53251649590675
aime26_18,26,503,"[12, '12']",True,False,150,16384,306.0663401680067
aime26_18,14,503,"[994, '994']",True,False,150,16384,346.7141564260237
aime26_18,12,503,"[16, '16']",True,False,150,16384,363.9250123889651
aime26_19,4,279,"[72, '72']",True,False,143,16384,308.4821824679384
aime26_18,21,503,"[2, '2']",True,False,150,16384,343.19027549400926
aime26_20,7,190,"[5, '5']",True,False,105,16384,246.2372808959335
aime26_17,16,243,"[252, '252']",True,False,369,16384,486.11388579697814
aime26_18,1,503,"[1, '1']",True,False,150,16384,430.17315595201217
aime26_19,1,279,"[10, '10']",True,False,143,16384,329.8499968700344
aime26_17,28,243,"[factorial(10), '10!']",True,False,369,16384,451.611593132955
aime26_18,19,503,"[-408, '-408']",True,False,150,16384,355.25456082692835
aime26_20,5,190,"[7, '7']",True,False,105,16384,262.14850947703235
aime26_20,15,190,"[190, '190']",True,True,105,16384,246.64696872700006
aime26_19,6,279,"[999, '999']",True,False,143,16384,330.541296524927
aime26_18,20,503,"[180, '180']",True,False,150,16384,365.49420865403954
aime26_18,28,503,"[1600 - 1*160, '1600 - 160']",True,False,150,16384,347.86353459290694
aime26_19,28,279,"[10, '10']",True,False,143,16384,289.5738632460125
aime26_18,29,503,"[196, '196']",True,False,150,16384,348.2922443379648
aime26_17,25,243,"[3, '3']",True,False,369,16383,481.1736256350996
aime26_19,25,279,"[999, '999']",True,False,143,16384,299.59965262701735
aime26_18,27,503,"[2**6*3*5, '2^6 * 3 * 5']",True,False,150,16384,356.4992286089109
aime26_18,9,503,"[2, '2']",True,False,150,16384,422.57052237400785
aime26_19,22,279,"[10, '10']",True,False,143,16384,307.65435945708305
aime26_19,23,279,"[1000, '1000']",True,False,143,16384,306.9495285029989
aime26_18,8,503,"[-2, '-2']",True,False,150,16384,433.5438640260836
aime26_19,19,279,"[999, '999']",True,False,143,16384,313.2768622559961
aime26_18,22,503,"[125, '125']",True,False,150,16384,380.0150910129305
aime26_18,0,503,"[0, '0']",True,False,150,16384,462.61269466008525
aime26_19,3,279,"[9, '9']",True,False,143,16384,359.40792947798036
aime26_18,30,503,"[30, '30']",True,False,150,16384,369.4929645799566
aime26_20,3,190,"[21, '21']",True,False,105,16389,300.7922949179774
aime26_19,18,279,"[9 + 90 + 90, '9 + 90 + 90']",True,False,143,16384,329.1443631310249
aime26_19,31,279,"[999, '999']",True,False,143,16384,315.50606699299533
aime26_20,10,190,"[7, '7']",True,False,105,16384,294.7112294610124
aime26_20,18,190,"[190, '190']",True,True,105,16387,283.3077301529702
aime26_19,30,279,['5*8 + '],True,False,143,16384,318.5193330720067
aime26_19,11,279,"[999, '999']",True,False,143,16384,349.4360787089681
aime26_19,5,279,"[0, '0']",True,False,143,16384,368.58832269907
aime26_20,19,190,"[5 - 1*1, '5 - 1']",True,False,105,16384,278.211101192981
aime26_19,20,279,"[9, '9']",True,False,143,16384,331.84142891399097
aime26_19,12,279,"[9, '9']",True,False,143,16384,350.12131175608374
aime26_18,17,503,"[45, '45']",True,False,150,16384,413.41671437805053
aime26_19,16,279,"[999, '999']",True,False,143,16384,345.388313716976
aime26_20,1,190,"[190, '190']",True,True,105,16384,326.3690607099561
aime26_20,23,190,"[190, '190']",True,True,105,16384,278.0869281409541
aime26_19,14,279,"[488, '488']",True,False,143,16384,353.58901292295195
aime26_19,26,279,"[999, '999']",True,False,143,16384,339.01860194001347
aime26_19,0,279,"[990, '990']",True,False,143,16384,397.3906103549525
aime26_20,31,190,"[515, '515']",True,False,105,16384,274.3788838200271
aime26_20,11,190,"[14, '14']",True,False,105,16384,314.6991762020625
aime26_20,21,190,"[190, '190']",True,True,105,16386,299.7105921320617
aime26_18,16,503,"[20, '20']",True,False,150,16384,437.9761678460054
aime26_19,21,279,"[10, '10']",True,False,143,16384,356.8219858621014
aime26_19,13,279,"[1, '1']",True,False,143,16384,372.86409916298
aime26_20,4,190,"[190, '190']",True,True,105,16387,338.809226318961
aime26_19,27,279,"[999, '999']",True,False,143,16384,358.4291153390659
aime26_18,25,503,['1/2)(1 +'],True,False,150,16384,424.62799170194194
aime26_19,29,279,"[10, '10']",True,False,143,16384,363.0420827160124
aime26_20,6,190,"[168, '168']",True,False,105,16384,350.21932142192964
aime26_18,24,503,"[3, '3']",True,False,150,16384,428.5748416839633
aime26_19,8,279,"[1100, '1100']",True,False,143,16384,406.70749400998466
aime26_20,26,190,"[16380, '16380']",True,False,105,16384,321.74154272302985
aime26_21,2,50,"[50, '50']",True,True,78,16384,299.93390292394906
aime26_19,17,279,"[1010, '1010']",True,False,143,16384,398.3641639020061
aime26_19,9,279,"[10, '10']",True,False,143,16384,416.9989080899395
aime26_20,13,190,"[-217, '-217']",True,False,105,16387,352.402182733058
aime26_20,27,190,"[16, '16']",True,False,105,16384,334.31620356300846
aime26_21,15,50,['41 + 9 +'],True,False,78,16384,262.613993027946
aime26_21,7,50,"[4*sqrt(10), '4\\sqrt{10}']",True,False,78,16384,291.44989300204907
aime26_20,14,190,"[3, '3']",True,False,105,16384,367.44100189604796
aime26_19,24,279,"[999, '999']",True,False,143,16384,409.84950627794024
aime26_20,8,190,"[1465, '1465']",True,False,105,16384,384.3626606100006
aime26_20,22,190,"[6.60000000000000, '6.6']",True,False,105,16384,361.66528597299475
aime26_20,0,190,"[190, '190']",True,True,105,16384,408.882195202983
aime26_21,31,50,"[9, '9']",True,False,78,16384,210.7323843470076
aime26_20,17,190,"[190, '190']",True,True,105,16386,392.2911203140393
aime26_20,29,190,"[3, '3']",True,False,105,16384,368.5679162570741
aime26_21,3,50,"[59, '59']",True,False,78,16384,350.6558081379626
aime26_22,4,754,['6).'],True,False,127,16384,211.48123246000614
aime26_20,30,190,"[637560, '637560']",True,False,105,16384,372.92703375802375
aime26_21,23,50,"[41, '41']",True,False,78,16384,253.0972562659299
aime26_20,16,190,"[190, '190']",True,True,105,16384,406.41751364804804
aime26_20,9,190,"[190, '190']",True,True,105,16384,418.44865975005087
aime26_21,10,50,"[12, '12']",True,False,78,16384,324.91871382202953
aime26_20,24,190,"[190, '190']",True,True,105,16384,393.9604027699679
aime26_21,18,50,"[78, '78']",True,False,78,16384,319.8047055740608
aime26_20,28,190,"[10, '10']",True,False,105,16384,413.7923369319178
aime26_22,15,754,"[6, '6']",True,False,127,16384,229.52608763298485
aime26_22,3,754,"[6, '6']",True,False,127,16384,261.2356324469438
aime26_21,26,50,"[9, '9']",True,False,78,16384,287.5125441250857
aime26_22,5,754,['(1/3'],True,False,127,16384,258.0018143609632
aime26_22,12,754,"[6, '6']",True,False,127,16384,248.80596434499603
aime26_21,6,50,"[9, '9']",True,False,78,16384,377.96133780502714
aime26_22,2,754,"[2/(3*(1 - 4/9)**2), '(2/3) / (1 - (4/9))^2']",True,False,127,16384,270.4477697870461
aime26_20,20,190,"[1225/3432, '1225 / 3432']",True,False,105,16385,446.19608742103446
aime26_22,11,754,"[6, '6']",True,False,127,16384,254.34507943305653
aime26_22,1,754,"[2, '2']",True,False,127,16384,281.1954249930568
aime26_22,6,754,"[6, '6']",True,False,127,16384,265.21796654805075
aime26_22,13,754,"[6, '6']",True,False,127,16384,252.52099832810927
aime26_22,14,754,['2/3). \n'],True,False,127,16384,254.66776625195052
aime26_20,12,190,"[1, '1']",True,False,105,16386,469.0507616470568
aime26_21,1,50,"[sqrt(201), '\\sqrt{201}']",True,False,78,16384,427.62554567004554
aime26_21,13,50,"[41, '41']",True,False,78,16384,369.37955417099874
aime26_20,25,190,"[674/115, '674 / 115']",True,False,105,16390,444.9782557069557
aime26_21,5,50,"[9, '9']",True,False,78,16384,417.71124340896495
aime26_22,21,754,"[1, '1']",True,False,127,16384,233.1466475330526
aime26_21,29,50,"[9, '9']",True,False,78,16384,302.9902574690059
aime26_21,22,50,"[9, '9']",True,False,78,16384,335.7458940439392
aime26_21,12,50,"[41, '41']",True,False,78,16384,384.82985955500044
aime26_21,11,50,"[50, '50']",True,True,78,16384,391.363073588931
aime26_21,27,50,"[59, '59']",True,False,78,16384,311.730253997026
aime26_21,4,50,"[0, '0']",True,False,78,16384,432.5539343659766
aime26_21,14,50,"[18, '18']",True,False,78,16384,385.1041150810197
aime26_21,17,50,"[1681, '1681']",True,False,78,16384,390.01395543909166
aime26_21,30,50,"[50, '50']",True,True,78,16384,324.59640388702974
aime26_21,19,50,"[25600 - 1*268, '25600 - 268']",True,False,78,16384,384.7437892490998
aime26_21,21,50,"[201, '201']",True,False,78,16384,365.37375150294974
aime26_22,10,754,"[829, '829']",True,False,127,16384,299.1713194149779
aime26_22,31,754,"[8/75.0, '8/75. \n']",True,False,127,16384,248.5292080710642
aime26_22,7,754,"[5, '5']",True,False,127,16384,308.5836004510056
aime26_21,20,50,"[50, '50']",True,True,78,16384,367.82448118098546
aime26_22,29,754,"[6, '6']",True,False,127,16384,253.8375841040397
aime26_21,8,50,"[9, '9']",True,False,78,16384,428.570697797928
aime26_23,7,245,"[2, '2']",True,False,91,16384,241.52321630797815
aime26_23,10,245,"[2, '2']",True,False,91,16384,239.88808647799306
aime26_23,18,245,"[1 + 2*600*11, '2*600*11 + 1']",True,False,91,16384,226.4554013289744
aime26_22,18,754,"[4, '4']",True,False,127,16384,287.10707725503016
aime26_21,28,50,"[720, '720']",True,False,78,16384,347.8597265910357
aime26_21,25,50,"[9, '9']",True,False,78,16384,358.28263482800685
aime26_22,23,754,"[17/27.0, '17/27. \n']",True,False,127,16384,279.3367207470583
aime26_21,9,50,"[0, '0']",True,False,78,16384,443.1886789170094
aime26_22,24,754,"[6, '6']",True,False,127,16384,291.00432221603114
aime26_21,0,50,"[41, '41']",True,False,78,16384,496.2535247770138
aime26_22,27,754,['3) +'],True,False,127,16384,298.3214470440289
aime26_21,16,50,"[80, '80']",True,False,78,16384,444.57889866793994
aime26_22,26,754,"[1 - 1*4.0, '1-4.']",True,False,127,16384,308.9855005580466
aime26_23,2,245,"[60052, '60052']",True,False,91,16384,290.89475323993247
aime26_22,19,754,['1) +'],True,False,127,16384,322.01069244008977
aime26_22,28,754,"[1 - 32/2, '1 - 32/2']",True,False,127,16384,301.41204253199976
aime26_23,11,245,"[2, '2']",True,False,91,16384,284.7868493819842
aime26_23,4,245,"[1, '1']",True,False,91,16384,300.2008611980127
aime26_21,24,50,"[39, '39']",True,False,78,16384,407.0160236679949
aime26_23,3,245,"[2, '2']",True,False,91,16384,303.5856904289685
aime26_22,17,754,"[1, '1']",True,False,127,16384,343.98909052298404
aime26_23,15,245,"[12, '12']",True,False,91,16384,283.2538833399303
aime26_22,22,754,"[409, '409']",True,False,127,16384,337.067302228068
aime26_23,31,245,"[250, '250']",True,False,91,16384,268.2960646050051
aime26_23,6,245,"[25.7000000000000, '25.7']",True,False,91,16384,308.9681834100047
aime26_22,8,754,"[1/3.0, '1/3.']",True,False,127,16384,381.0462423119461
aime26_24,7,669,"[1, '1']",True,False,108,16384,257.32992249692325
aime26_23,23,245,"[2, '2']",True,False,91,16382,305.06484266300686
aime26_24,15,669,"[1, '1']",True,False,108,16384,249.61108902993146
aime26_23,27,245,"[125/6.0, '125/6.']",True,False,91,16384,301.14529025007505
aime26_23,29,245,"[4, '4']",True,False,91,16384,297.5818314519711
aime26_23,19,245,"[2*2, '2*2']",True,False,91,16384,315.0355262879748
aime26_23,21,245,['(2.449 + 1.41'],True,False,91,16384,314.3555376000004
aime26_23,12,245,"[6, '6']",True,False,91,16384,327.5571242129663
aime26_23,26,245,['(5/2) /'],True,False,91,16384,310.51171361503657
aime26_24,2,669,"[159, '159']",True,False,108,16384,294.656453214935
aime26_22,20,754,"[409, '409']",True,False,127,16384,376.95176020404324
aime26_23,14,245,"[30750, '30750']",True,False,91,16384,327.8586186940083
aime26_22,30,754,"[1/3.0, '1/3.']",True,False,127,16384,362.9791588849621
aime26_23,5,245,"[2, '2']",True,False,91,16383,350.218542879913
aime26_23,13,245,"[6, '6']",True,False,91,16384,340.3218289640499
aime26_25,2,850,"[0, '0']",True,False,168,16384,205.62281533703208
aime26_22,0,754,"[4/81.0, '4/81. \n']",True,False,127,16384,442.4225423129974
aime26_23,1,245,"[1, '1']",True,False,91,16384,359.99033316096757
aime26_23,9,245,['(2*5 - '],True,False,91,16384,349.2910459539853
aime26_24,14,669,"[1, '1']",True,False,108,16384,273.7254154639086
aime26_22,25,754,"[404, '404']",True,False,127,16384,378.8202398370486
aime26_23,22,245,"[4, '4']",True,False,91,16384,333.39423797803465
aime26_24,10,669,"[11/90, '11/90']",True,False,108,16384,292.6574151760433
aime26_22,9,754,"[1/6.0, '1/6. \n']",True,False,127,16384,432.9347954749828
aime26_23,17,245,"[2, '2']",True,False,91,16384,345.44179236795753
aime26_23,0,245,"[1, '1']",True,False,91,16384,377.8215694470564
aime26_24,23,669,"[0.1111 - 1*0.001, '0.1111 - 0.00100']",True,False,108,16384,258.7262624569703
aime26_22,16,754,"[4/9.0, '4/9. \n']",True,False,127,16384,420.2012946830364
aime26_23,20,245,['1)^'],True,False,91,16383,351.0072485530982
aime26_23,16,245,"[2, '2']",True,False,91,16384,357.60044612607453
aime26_24,19,669,"[1, '1']",True,False,108,16384,277.1862872670172
aime26_23,30,245,['2 )\n'],True,False,91,16384,339.10205452807713
aime26_24,13,669,"[10, '10']",True,False,108,16384,310.7158418010222
aime26_24,3,669,"[10**102, '10^102']",True,False,108,16384,340.4365843679989
aime26_24,31,669,['1/9 + 1/'],True,False,108,16384,251.03937909693923
aime26_24,5,669,"[81, '81']",True,False,108,16384,346.727816308965
aime26_24,11,669,"[0, '0']",True,False,108,16384,329.51496967999265
aime26_23,8,245,"[5, '5']",True,False,91,16384,403.1274079839932
aime26_25,7,850,"[225, '225']",True,False,168,16384,225.38752485706937
aime26_24,6,669,['1/9 +'],True,False,108,16384,350.9497591810068
aime26_24,18,669,"[959, '959']",True,False,108,16384,318.66658842994366
aime26_24,22,669,"[0, '0']",True,False,108,16384,309.65769746294245
aime26_24,21,669,"[11, '11']",True,False,108,16384,310.0025919089094
aime26_23,28,245,['1/4 +'],True,False,91,16384,383.1176959699951
aime26_23,24,245,"[125, '125']",True,False,91,16384,393.02482702198904
aime26_24,9,669,['1).'],True,False,108,16384,360.37931649794336
aime26_24,20,669,"[0.001 + 0.1212121212, '0.1212121212\n\n+ 0.00100']",True,False,108,16384,323.84217543399427
aime26_24,26,669,"[1, '1']",True,False,108,16384,301.0743780309567
aime26_24,29,669,"[1.00001000000000e-7, '0.000000100001000']",True,False,108,16384,293.264414921985
aime26_25,4,850,"[0, '0']",True,False,168,16384,268.9971168859629
aime26_24,0,669,['10/90 - 9/'],True,False,108,16384,390.39416054205503
aime26_26,7,132,"[400, '400']",True,False,121,16384,196.34600565594155
aime26_24,1,669,"[9680, '9680']",True,False,108,16384,395.2841258139815
aime26_24,4,669,"[35, '35']",True,False,108,16384,394.70465906895697
aime26_23,25,245,['4 ). \n'],True,False,91,16384,419.5996960620396
aime26_24,30,669,['100...000 - 00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000'],True,False,108,16384,310.5852227190044
aime26_24,12,669,"[901, '901']",True,False,108,16384,373.3950782819884
aime26_24,27,669,"[345, '345']",True,False,108,16384,330.3165084209759
aime26_25,13,850,"[13020000, '13020000']",True,False,168,16384,274.6318955369061
aime26_24,28,669,"[-1/999 + 1/9, '1/9 - 1/999']",True,False,108,16384,333.7744311679853
aime26_24,17,669,['1/9 + 1/99 + 1/999 + 1/9999 +'],True,False,108,16384,377.6195642630337
aime26_26,2,132,"[400, '400']",True,False,121,16384,245.23731272295117
aime26_25,10,850,"[2, '2']",True,False,168,16384,296.4081261019455
aime26_24,25,669,"[111, '111']",True,False,108,16384,364.9745882229181
aime26_25,6,850,"[64, '64']",True,False,168,16384,311.03035184391774
aime26_25,1,850,"[2, '2']",True,False,168,16384,344.3126967009157
aime26_25,21,850,"[8, '8']",True,False,168,16384,295.46186500496697
aime26_25,3,850,"[5100, '5100']",True,False,168,16383,348.4158036389854
aime26_25,15,850,"[9, '9']",True,False,168,16384,305.04654650809243
aime26_25,5,850,"[8, '8']",True,False,168,16384,322.6960337560158
aime26_24,8,669,"[111, '111']",True,False,108,16384,436.822573813959
aime26_25,22,850,"[140000, '140000']",True,False,168,16384,306.6078580680769
aime26_25,23,850,"[2, '2']",True,False,168,16384,308.0894521549344
aime26_25,18,850,"[0, '0']",True,False,168,16384,314.06009827693924
aime26_27,2,223,"[18, '18']",True,False,166,16384,212.84374404896516
aime26_25,30,850,"[765, '765']",True,False,168,16384,307.9859063240001
aime26_25,14,850,"[595, '595']",True,False,168,16384,334.4473948919913
aime26_26,5,132,"[2, '2']",True,False,121,16384,294.3074756839778
aime26_25,12,850,['0).'],True,False,168,16384,344.482249559951
aime26_25,26,850,"[425, '425']",True,False,168,16384,322.41304246499203
aime26_25,31,850,"[225, '225']",True,False,168,16384,317.19177402590867
aime26_24,24,669,"[0, '0']",True,False,108,16384,423.428264503018
aime26_26,10,132,"[346562, '346562']",True,False,121,16384,292.328469144064
aime26_24,16,669,"[0, '0']",True,False,108,16384,453.3190098120831
aime26_25,11,850,"[2, '2']",True,False,168,16384,352.4471327490173
aime26_25,20,850,"[375, '375']",True,False,168,16384,344.0237119909143
aime26_25,9,850,"[0, '0']",True,False,168,16384,370.856116447947
aime26_26,18,132,"[4, '4']",True,False,121,16384,293.91506381402723
aime26_25,27,850,"[36, '36']",True,False,168,16384,350.38735675101634
aime26_26,3,132,"[400, '400']",True,False,121,16384,328.9357591769658
aime26_25,29,850,"[22, '22']",True,False,168,16384,351.78513580199797
aime26_26,26,132,"[1, '1']",True,False,121,16383,272.3827625819249
aime26_25,19,850,"[0, '0']",True,False,168,16384,369.1639384099981
aime26_25,0,850,"[8, '8']",True,False,168,16384,426.7061020738911
aime26_26,15,132,"[2, '2']",True,False,121,16384,319.5460303579457
aime26_26,17,132,"[400, '400']",True,False,121,16384,313.18350551708136
aime26_26,23,132,"[6, '6']",True,False,121,16384,288.85337420203723
aime26_26,4,132,"[2511040.25000000, '2511040.25']",True,False,121,16384,344.2576297580963
aime26_25,28,850,"[2, '2']",True,False,168,16384,371.26953098294325
aime26_25,16,850,"[16, '16']",True,False,168,16384,398.0016696980456
aime26_26,19,132,"[11, '11']",True,False,121,16384,329.2378715300001
aime26_25,17,850,"[85, '85']",True,False,168,16384,400.92357789503876
aime26_27,7,223,"[88.5000000000000, '88.5']",True,False,166,16384,268.76789214706514
aime26_25,25,850,"[2, '2']",True,False,168,16384,391.3199982889928
aime26_25,8,850,"[850, '850']",True,True,168,16384,418.86191915592644
aime26_26,13,132,"[3, '3']",True,False,121,16384,356.94788720598444
aime26_26,11,132,"[400, '400']",True,False,121,16384,369.1258072779747
aime26_26,31,132,"[11, '11']",True,False,121,16384,313.0753259359626
aime26_27,10,223,"[-5, '-5']",True,False,166,16384,280.12512652098667
aime26_26,14,132,"[0, '0']",True,False,121,16384,367.38143343897536
aime26_26,6,132,"[40, '40']",True,False,121,16384,380.7845742580248
aime26_26,0,132,"[400, '400']",True,False,121,16384,391.8119989039842
aime26_26,21,132,"[12, '12']",True,False,121,16384,341.4780967690749
aime26_27,26,223,"[9, '9']",True,False,166,16384,268.61445702204946
aime26_27,27,223,"[1/6, '1/6']",True,False,166,16384,263.47624559199903
aime26_26,1,132,"[0, '0']",True,False,121,16384,397.14063037908636
aime26_26,29,132,"[2, '2']",True,False,121,16384,329.1530249520438
aime26_26,12,132,"[12.6660000000000, '12.666']",True,False,121,16384,381.69837557605933
aime26_27,18,223,"[1, '1']",True,False,166,16384,279.94133954902645
aime26_27,23,223,"[19, '19']",True,False,166,16384,282.1705578939291
aime26_27,3,223,['250 - 888/'],True,False,166,16384,325.1897300740238
aime26_27,15,223,"[18, '18']",True,False,166,16384,295.15986891894136
aime26_25,24,850,"[-407.500000000000, '-407.5']",True,False,168,16384,435.3003467550734
aime26_26,9,132,"[2, '2']",True,False,121,16384,400.52822423900943
aime26_27,11,223,"[0, '0']",True,False,166,16384,307.2872026358964
aime26_26,27,132,"[0, '0']",True,False,121,16384,348.2330906619318
aime26_28,6,107,"[1, '1']",True,False,147,16384,254.6807672129944
aime26_27,31,223,"[5, '5']",True,False,166,16384,278.93404176901095
aime26_26,30,132,"[66, '66']",True,False,121,16384,347.2150179500459
aime26_26,22,132,"[3, '3']",True,False,121,16384,365.8817514020484
aime26_26,20,132,"[400, '400']",True,False,121,16384,374.3112427009037
aime26_27,14,223,"[117, '117']",True,False,166,16384,314.95804561895784
aime26_26,25,132,"[-1.75000000000000, '-1.75']",True,False,121,16384,373.4584026261
aime26_26,8,132,"[4, '4']",True,False,121,16384,423.0948523900006
aime26_27,6,223,"[25, '25']",True,False,166,16384,337.8629020479275
aime26_27,13,223,"[33, '33']",True,False,166,16384,326.9846119219437
aime26_27,5,223,"[2, '2']",True,False,166,16359,342.8890575240366
aime26_26,28,132,"[-11.4190000000000, '-11.419']",True,False,121,16384,379.0646543140756
aime26_27,21,223,['(20/3 - 45/3)^2 +'],True,False,166,16384,323.72146556002554
aime26_27,1,223,"[1, '1']",True,False,166,16384,366.54464890400413
aime26_27,4,223,"[3, '3']",True,False,166,16384,361.90259542304557
aime26_27,29,223,['(13858 - 23'],True,False,166,16384,317.4115779439453
aime26_26,16,132,"[6, '6']",True,False,121,16384,431.3276608479209
aime26_28,10,107,"[1, '1']",True,False,147,16384,282.0846736780368
aime26_27,22,223,"[250, '250']",True,False,166,16384,346.0215881970944
aime26_27,0,223,"[18, '18']",True,False,166,16384,393.94126045296434
aime26_27,9,223,['53.2 + (42'],True,False,166,16384,378.9539484800771
aime26_27,28,223,"[3, '3']",True,False,166,16384,349.6967982639326
aime26_27,16,223,"[1, '1']",True,False,166,16384,365.5754593710881
aime26_27,8,223,['(-50000 / 324) * (18'],True,False,166,16384,381.89706672297325
aime26_27,19,223,"[151/2, '151/2']",True,False,166,16384,365.2360630449839
aime26_28,12,107,"[2, '2']",True,False,147,16384,304.1952334990492
aime26_27,17,223,['4) *'],True,False,166,16384,369.66012714698445
aime26_28,7,107,"[1, '1']",True,False,147,16384,323.19515450601466
aime26_27,12,223,"[3, '3']",True,False,166,16384,383.288970669033
aime26_28,29,107,"[2, '2']",True,False,147,16384,262.5571686270414
aime26_28,2,107,"[4040, '4040']",True,False,147,16384,348.17122988798656
aime26_27,30,223,['(25*10)/4 +'],True,False,166,16384,358.17963873106055
aime26_29,26,157,"[0, '0']",True,False,195,16384,175.19872806896456
aime26_27,20,223,['(250 - 8'],True,False,166,16384,381.5267905300716
aime26_29,6,157,"[0, '0']",True,False,195,16384,242.8748624570435
aime26_28,18,107,"[2, '2']",True,False,147,16383,314.10582473804243
aime26_28,23,107,"[4, '4']",True,False,147,16384,308.73773305490613
aime26_27,25,223,"[3, '3']",True,False,166,16379,390.3287081370363
aime26_29,7,157,"[0, '0']",True,False,195,16384,255.01091545901727
aime26_26,24,132,"[400, '400']",True,False,121,16384,465.22309615300037
aime26_28,5,107,"[4040, '4040']",True,False,147,16384,364.6718965120381
aime26_28,15,107,"[1, '1']",True,False,147,16384,344.20414905890357
aime26_29,10,157,"[1, '1']",True,False,195,16384,264.0218444929924
aime26_28,30,107,"[11, '11']",True,False,147,16384,300.4004400020931
aime26_29,2,157,"[0, '0']",True,False,195,16384,284.62930131005123
aime26_29,15,157,"[0, '0']",True,False,195,16384,244.5880734800594
aime26_29,3,157,"[0, '0']",True,False,195,16384,288.2222618589876
aime26_28,26,107,"[1, '1']",True,False,147,16384,329.56962192594074
aime26_29,23,157,"[12, '12']",True,False,195,16384,240.92834797501564
aime26_28,4,107,"[1, '1']",True,False,147,16384,393.4492038799217
aime26_28,13,107,"[4040, '4040']",True,False,147,16384,369.1576433168957
aime26_29,12,157,"[12, '12']",True,False,195,16384,279.49940930493176
aime26_28,31,107,"[1, '1']",True,False,147,16384,326.54274887696374
aime26_29,18,157,"[0, '0']",True,False,195,16384,264.6259099270683
aime26_28,14,107,"[3, '3']",True,False,147,16384,389.1993961900007
aime26_28,1,107,"[6, '6']",True,False,147,16384,429.12123020901345
aime26_29,13,157,"[5, '5']",True,False,195,16384,296.7166396569228
aime26_28,3,107,"[1, '1']",True,False,147,16383,433.07488342910074
aime26_30,10,393,"[1, '1']",True,False,185,16384,218.16461065702606
aime26_28,21,107,"[2, '2']",True,False,147,16384,387.40415473806206
aime26_28,11,107,"[4040, '4040']",True,False,147,16383,414.7845958870603
aime26_29,14,157,"[6, '6']",True,False,195,16384,299.7885254200082
aime26_30,2,393,"[3, '3']",True,False,185,16384,252.9077134410618
aime26_29,21,157,"[2, '2']",True,False,195,16384,288.492613469949
aime26_28,9,107,"[15, '15']",True,False,147,16384,418.55128681694623
aime26_29,30,157,"[0, '0']",True,False,195,16384,267.50345164199825
aime26_28,20,107,"[4040, '4040']",True,False,147,16384,406.1472451380687
aime26_29,5,157,"[0, '0']",True,False,195,16384,349.3457888410194
aime26_29,19,157,"[0, '0']",True,False,195,16384,304.6325058559887
aime26_29,1,157,"[0, '0']",True,False,195,16384,361.89264755300246
aime26_28,19,107,"[5, '5']",True,False,147,16384,413.0106003918918
aime26_29,17,157,"[0, '0']",True,False,195,16384,310.18830033100676
aime26_28,22,107,"[4040, '4040']",True,False,147,16384,408.40169036900625
aime26_29,22,157,"[0, '0']",True,False,195,16384,305.8234552589711
aime26_30,15,393,"[7, '7']",True,False,185,16384,229.84034490399063
aime26_30,6,393,"[0, '0']",True,False,185,16384,261.6910111969337
aime26_28,28,107,"[1, '1']",True,False,147,16384,397.5223415509099
aime26_30,18,393,"[3, '3']",True,False,185,16384,235.98915242298972
aime26_29,31,157,"[0, '0']",True,False,195,16384,288.0310865039937
aime26_30,23,393,"[3, '3']",True,False,185,16384,226.21435520600062
aime26_28,16,107,"[4040, '4040']",True,False,147,16384,437.0885142890038
aime26_30,5,393,"[3, '3']",True,False,185,16384,276.11337151401676
aime26_29,20,157,"[12, '12']",True,False,195,16384,323.71289420092944
aime26_30,26,393,"[2282, '2282']",True,False,185,16384,228.61091381602455
aime26_30,31,393,"[3, '3']",True,False,185,16384,220.9454531579977
aime26_29,9,157,"[0, '0']",True,False,195,16384,365.98939842393156
aime26_28,27,107,"[4, '4']",True,False,147,16384,413.54195650399197
aime26_27,24,223,"[0, '0']",True,False,166,16384,509.60956014401745
aime26_30,7,393,"[3, '3']",True,False,185,16384,274.531192565104
aime26_30,14,393,"[6 - 1*1, '6-1']",True,False,185,16384,252.34907890995964
aime26_28,8,107,"[4040, '4040']",True,False,147,16384,471.27135416003875
aime26_29,28,157,"[0, '0']",True,False,195,16384,310.93023310997523
aime26_29,4,157,"[1, '1']",True,False,195,16384,391.9891784579959
aime26_28,0,107,"[4, '4']",True,False,147,16384,505.383636360988
aime26_28,17,107,"[1, '1']",True,False,147,16383,454.0392167819664
aime26_30,3,393,"[3, '3']",True,False,185,16384,311.4696423159912
aime26_29,11,157,"[12, '12']",True,False,195,16384,376.3988845749991
aime26_29,29,157,"[0, '0']",True,False,195,16384,326.045277684927
aime26_29,8,157,"[0, '0']",True,False,195,16384,396.0882890729699
aime26_30,29,393,"[1, '1']",True,False,185,16384,260.66181260102894
aime26_29,24,157,"[0, '0']",True,False,195,16384,363.2450173749821
aime26_30,21,393,"[3, '3']",True,False,185,16384,276.3218860719353
aime26_28,25,107,"[1, '1']",True,False,147,16384,461.33869856398087
aime26_30,30,393,"[1, '1']",True,False,185,16384,266.3951059760293
aime26_30,1,393,"[-3, '-3']",True,False,185,16384,341.9343742020428
aime26_30,20,393,"[3, '3']",True,False,185,16384,285.0949383949628
aime26_30,12,393,"[3, '3']",True,False,185,16384,310.40236104500946
aime26_29,0,157,"[-1, '-1']",True,False,195,16384,442.3704013460083
aime26_30,13,393,"[5, '5']",True,False,185,16384,315.3205573580926
aime26_30,28,393,"[3, '3']",True,False,185,16384,285.3780611830298
aime26_29,27,157,"[2, '2']",True,False,195,16384,363.95382094103843
aime26_30,11,393,"[48, '48']",True,False,185,16384,324.5613489219686
aime26_30,22,393,"[27, '27']",True,False,185,16384,298.6861351990374
aime26_30,4,393,"[5, '5']",True,False,185,16384,356.6518262309255
aime26_29,25,157,"[12, '12']",True,False,195,16384,392.1982599910116
aime26_30,19,393,"[2, '2']",True,False,185,16384,314.85609510401264
aime26_30,0,393,"[1, '1']",True,False,185,16384,369.5454224089626
aime26_30,27,393,"[7, '7']",True,False,185,16384,309.29820779094007
aime26_28,24,107,"[1, '1']",True,False,147,16384,514.7952828869456
aime26_30,16,393,"[3, '3']",True,False,185,16384,350.6233414460439
aime26_30,17,393,"[3, '3']",True,False,185,16384,369.23099841491785
aime26_29,16,157,"[4, '4']",True,False,195,16384,466.6430242009228
aime26_30,9,393,"[1, '1']",True,False,185,16384,396.09432519890834
aime26_30,8,393,"[225, '225']",True,False,185,16384,407.1750580120133
aime26_30,25,393,"[9, '9']",True,False,185,16384,375.7892609159462
aime26_30,24,393,"[0, '0']",True,False,185,16384,382.94195019907784
1 problem_id sample_idx correct_answer predicted_answer has_answer is_correct input_tokens output_tokens processing_time
2 aime26_1 15 277 [277, '277'] True True 166 16384 134.77429561095778
3 aime26_1 13 277 [277, '277'] True True 166 16384 135.70280905696563
4 aime26_1 31 277 [277, '277'] True True 166 16384 137.5812207129784
5 aime26_1 1 277 [277, '277'] True True 166 16384 140.64982309704646
6 aime26_1 12 277 [277, '277'] True True 166 16384 142.44176353001967
7 aime26_1 2 277 [277, '277'] True True 166 16384 142.46094795805402
8 aime26_1 20 277 [277, '277'] True True 166 16384 143.52319206099492
9 aime26_1 10 277 [277, '277'] True True 166 16384 143.6126011540182
10 aime26_1 7 277 [277, '277'] True True 166 16384 145.01237725489773
11 aime26_3 16 79 [42, '42'] True False 137 16384 145.38743539701682
12 aime26_1 25 277 [277, '277'] True True 166 16384 146.46217927301768
13 aime26_1 16 277 [277, '277'] True True 166 16384 147.27775920392014
14 aime26_1 24 277 [277, '277'] True True 166 16383 149.63286338292528
15 aime26_1 9 277 [277, '277'] True True 166 16384 151.64027504296973
16 aime26_1 18 277 [277, '277'] True True 166 16384 151.76163151301444
17 aime26_1 21 277 [277, '277'] True True 166 16384 155.11816306505352
18 aime26_1 22 277 [277, '277'] True True 166 16383 155.7441281210631
19 aime26_1 8 277 [277, '277'] True True 166 16384 158.9973271630006
20 aime26_1 29 277 [277, '277'] True True 166 16383 159.5448646149598
21 aime26_1 30 277 [277, '277'] True True 166 16384 165.74750621290877
22 aime26_1 23 277 [277, '277'] True True 166 16384 170.303320811945
23 aime26_1 19 277 [277, '277'] True True 166 16384 177.1560318999691
24 aime26_1 26 277 [277, '277'] True True 166 16384 177.59984589007217
25 aime26_1 6 277 [277, '277'] True True 166 16384 178.32823404797819
26 aime26_1 28 277 [277, '277'] True True 166 16382 178.4438678630395
27 aime26_3 5 79 [42, '42'] True False 137 16384 179.7478447520407
28 aime26_1 27 277 [277, '277'] True True 166 16384 180.93286803003866
29 aime26_2 1 62 [5, '5'] True False 85 16384 193.99506234005094
30 aime26_1 0 277 [277, '277'] True True 166 16384 199.12051617202815
31 aime26_1 3 277 [277, '277'] True True 166 16384 200.43822061899118
32 aime26_3 18 79 [200, '200'] True False 137 16384 201.21330349089112
33 aime26_3 7 79 [42, '42'] True False 137 16384 202.4101251210086
34 aime26_1 5 277 [277, '277'] True True 166 16384 202.68894911906682
35 aime26_3 22 79 [1, '1'] True False 137 16384 202.91442278400064
36 aime26_1 4 277 [277, '277'] True True 166 16384 210.52554363198578
37 aime26_3 10 79 [1, '1'] True False 137 16384 210.51481898198836
38 aime26_3 20 79 [19559, '19559'] True False 137 16384 212.70852139103226
39 aime26_2 28 62 ['8 + 2 +'] True False 85 16384 213.93810114997905
40 aime26_3 11 79 [1, '1'] True False 137 16384 215.20402541593648
41 aime26_3 14 79 [1, '1'] True False 137 16384 215.86283546697814
42 aime26_3 2 79 [1, '1'] True False 137 16384 220.69986831198912
43 aime26_3 8 79 [1, '1'] True False 137 16384 223.30379689496476
44 aime26_3 9 79 [2, '2'] True False 137 16384 225.22161486791447
45 aime26_1 14 277 [277, '277'] True True 166 16367 226.25752619595733
46 aime26_3 1 79 ['0).'] True False 137 16384 226.91208929906134
47 aime26_2 21 62 [79, '79'] True False 85 16384 231.91068653506227
48 aime26_2 13 62 [12, '12'] True False 85 16384 233.54165580193512
49 aime26_2 22 62 ['15 + ..'] True False 85 16384 236.7954011040274
50 aime26_1 11 277 [277, '277'] True True 166 16383 238.11334624898154
51 aime26_1 17 277 [277, '277'] True True 166 16383 239.68234283698257
52 aime26_2 7 62 [21, '21'] True False 85 16384 240.87529073399492
53 aime26_2 2 62 [15, '15'] True False 85 16384 243.22475534293335
54 aime26_3 15 79 [79, '79'] True True 137 16384 246.24098540702835
55 aime26_2 19 62 [38, '38'] True False 85 16384 247.4478938500397
56 aime26_2 24 62 [20, '20'] True False 85 16384 248.8499762819847
57 aime26_3 4 79 [1, '1'] True False 137 16384 251.9827228419017
58 aime26_2 5 62 [15, '15'] True False 85 16384 253.76852888101712
59 aime26_2 6 62 [33, '33'] True False 85 16384 255.56374050001614
60 aime26_2 17 62 [10, '10'] True False 85 16384 256.3175705879694
61 aime26_2 8 62 [1, '1'] True False 85 16384 257.2149356539594
62 aime26_3 23 79 [71, '71'] True False 137 16384 257.68887995695695
63 aime26_2 30 62 [41, '41'] True False 85 16384 259.19368692091666
64 aime26_2 10 62 [31, '31'] True False 85 16384 260.99050025001634
65 aime26_2 27 62 [25, '25'] True False 85 16384 261.024043885991
66 aime26_2 14 62 [15, '15'] True False 85 16384 262.24784782505594
67 aime26_2 11 62 [34, '34'] True False 85 16384 262.4699011539342
68 aime26_2 9 62 [2, '2'] True False 85 16384 263.8300104599912
69 aime26_3 6 79 [84, '84'] True False 137 16384 263.85455420194194
70 aime26_2 29 62 [1, '1'] True False 85 16384 263.9862668890273
71 aime26_2 16 62 [7, '7'] True False 85 16381 265.31413158297073
72 aime26_3 13 79 [1, '1'] True False 137 16384 266.3195504330797
73 aime26_2 31 62 [20, '20'] True False 85 16384 266.44462551397737
74 aime26_3 3 79 [2, '2'] True False 137 16384 266.60481508099474
75 aime26_3 17 79 [42, '42'] True False 137 16381 266.8133812039159
76 aime26_3 27 79 [2, '2'] True False 137 16384 267.78353567793965
77 aime26_2 18 62 [1, '1'] True False 85 16384 267.8152889449848
78 aime26_3 19 79 [1, '1'] True False 137 16384 268.01955140801147
79 aime26_3 25 79 ['0). \n'] True False 137 16384 268.45931235002354
80 aime26_3 0 79 [200, '200'] True False 137 16384 268.6021874679718
81 aime26_2 20 62 [53, '53'] True False 85 16384 269.1456529139541
82 aime26_2 26 62 [2, '2'] True False 85 16384 269.37000368197914
83 aime26_3 12 79 [1, '1'] True False 137 16384 269.3882264170097
84 aime26_2 4 62 [5, '5'] True False 85 16384 271.1305088130757
85 aime26_2 25 62 [10, '10'] True False 85 16384 271.80767492891755
86 aime26_2 3 62 [20, '20'] True False 85 16384 272.0920067370171
87 aime26_3 21 79 [158, '158'] True False 137 16384 273.6149851169903
88 aime26_2 0 62 [13, '13'] True False 85 16384 277.14474883896764
89 aime26_3 31 79 [2, '2'] True False 137 16384 277.20269135397393
90 aime26_2 15 62 [1, '1'] True False 85 16384 279.2785099640023
91 aime26_2 12 62 [5, '5'] True False 85 16384 281.8623461809475
92 aime26_3 26 79 [24, '24'] True False 137 16384 286.6085271689808
93 aime26_2 23 62 [9, '9'] True False 85 16384 286.6683547779685
94 aime26_3 30 79 [2941, '2941'] True False 137 16384 295.6460845649708
95 aime26_4 9 70 [6, '6'] True False 52 16384 300.2693157029571
96 aime26_4 7 70 [93, '93'] True False 52 16384 306.53644823806826
97 aime26_3 28 79 [2, '2'] True False 137 16384 307.12566971196793
98 aime26_3 24 79 [42, '42'] True False 137 16384 308.15283098700456
99 aime26_4 6 70 [90, '90'] True False 52 16384 313.9075435199775
100 aime26_4 15 70 [89, '89'] True False 52 16384 315.3880027459236
101 aime26_3 29 79 [10441, '10441'] True False 137 16384 317.344813385047
102 aime26_4 13 70 [70, '70'] True True 52 16384 339.27699473907705
103 aime26_4 3 70 [25, '25'] True False 52 16384 342.49224420497194
104 aime26_4 4 70 [64, '64'] True False 52 16384 345.90755764604546
105 aime26_4 0 70 [80, '80'] True False 52 16384 354.0466026660288
106 aime26_4 1 70 [137, '137'] True False 52 16384 356.06160642101895
107 aime26_4 5 70 [4, '4'] True False 52 16384 364.69486096606124
108 aime26_4 17 70 [70, '70'] True True 52 16384 369.4114956909325
109 aime26_4 19 70 [100, '100'] True False 52 16384 370.32856125803664
110 aime26_4 8 70 [66, '66'] True False 52 16384 371.17139041190967
111 aime26_5 0 65 [65, '65'] True True 152 16384 244.0956783130532
112 aime26_4 16 70 [65, '65'] True False 52 16384 379.1838457019767
113 aime26_5 4 65 [65, '65'] True True 152 16384 242.97654366202187
114 aime26_4 28 70 [86, '86'] True False 52 16384 386.40498800296336
115 aime26_4 2 70 [22, '22'] True False 52 16384 388.03078531997744
116 aime26_4 18 70 [88, '88'] True False 52 16384 393.68520379206166
117 aime26_4 11 70 [90, '90'] True False 52 16384 398.95809898199514
118 aime26_4 26 70 [74, '74'] True False 52 16384 399.3929473620374
119 aime26_4 10 70 [71, '71'] True False 52 16384 402.3715633730171
120 aime26_4 23 70 [173, '173'] True False 52 16384 404.6356968980981
121 aime26_4 21 70 [7, '7'] True False 52 16384 405.4388154600747
122 aime26_4 12 70 [137, '137'] True False 52 16384 407.3292882019887
123 aime26_6 11 441 [80, '80'] True False 68 16384 184.09987885691226
124 aime26_5 10 65 [65, '65'] True True 152 16384 271.7769234320149
125 aime26_4 27 70 [89, '89'] True False 52 16384 418.9449963020161
126 aime26_4 14 70 [65, '65'] True False 52 16384 422.27992245706264
127 aime26_4 29 70 [70, '70'] True True 52 16384 427.2406752840616
128 aime26_4 30 70 [71, '71'] True False 52 16384 428.3074553500628
129 aime26_5 8 65 [65, '65'] True True 152 16384 284.08525902905967
130 aime26_5 19 65 [65, '65'] True True 152 16384 267.3711293839151
131 aime26_5 2 65 [65, '65'] True True 152 16384 295.6914254829753
132 aime26_5 16 65 [65, '65'] True True 152 16384 281.2947311960161
133 aime26_5 23 65 [65, '65'] True True 152 16384 259.54872516193427
134 aime26_5 7 65 [29/36.0, '29/36.'] True False 152 16384 295.23566888505593
135 aime26_4 31 70 [137, '137'] True False 52 16384 445.6308536210563
136 aime26_5 11 65 [65, '65'] True True 152 16384 298.80851617397275
137 aime26_4 25 70 [7, '7'] True False 52 16384 449.8943001149455
138 aime26_5 29 65 [65, '65'] True True 152 16384 250.0648035829654
139 aime26_5 18 65 [65, '65'] True True 152 16384 291.0090890380088
140 aime26_5 1 65 [65, '65'] True True 152 16384 314.9012257499853
141 aime26_4 24 70 [137, '137'] True False 52 16384 455.37425539200194
142 aime26_4 22 70 [137, '137'] True False 52 16384 457.00957956002094
143 aime26_5 5 65 ['1).'] True False 152 16384 316.60183208889794
144 aime26_5 9 65 ['1).'] True False 152 16384 315.48646077606827
145 aime26_5 22 65 [65, '65'] True True 152 16384 286.92756386403926
146 aime26_4 20 70 [75, '75'] True False 52 16384 465.49895110109355
147 aime26_5 14 65 [4, '4'] True False 152 16384 318.85154722305015
148 aime26_5 31 65 [65, '65'] True True 152 16384 273.8667798630195
149 aime26_5 20 65 [65, '65'] True True 152 16384 309.81952702300623
150 aime26_6 2 441 [441, '441'] True True 68 16384 270.2245807880536
151 aime26_6 12 441 [441, '441'] True True 68 16384 258.71722224901896
152 aime26_5 27 65 [44, '44'] True False 152 16384 292.25113211700227
153 aime26_5 6 65 [5, '5'] True False 152 16384 343.1885427159723
154 aime26_6 5 441 [4, '4'] True False 68 16384 276.09153428603895
155 aime26_5 25 65 [-1*0.033 - 1*0 + 0.343, '0.343 - 0.0330 - 0'] True False 152 16384 311.8192951969104
156 aime26_5 3 65 [65, '65'] True True 152 16384 351.66651753301267
157 aime26_5 26 65 [6, '6'] True False 152 16384 311.70235578506254
158 aime26_5 17 65 [65, '65'] True True 152 16383 334.817371246987
159 aime26_5 21 65 [0, '0'] True False 152 16384 317.9936677310616
160 aime26_6 0 441 [4, '4'] True False 68 16384 292.54528923204634
161 aime26_6 18 441 [441, '441'] True True 68 16384 257.47149496199563
162 aime26_5 12 65 ['(1 - 2'] True False 152 16384 353.0499069900252
163 aime26_6 1 441 [441, '441'] True True 68 16384 301.41181612899527
164 aime26_6 29 441 [441, '441'] True True 68 16384 246.06771693995688
165 aime26_5 15 65 [65, '65'] True True 152 16384 350.5156113059493
166 aime26_5 13 65 [90, '90'] True False 152 16384 354.67130293895025
167 aime26_6 19 441 [200, '200'] True False 68 16384 268.46950695302803
168 aime26_6 15 441 [441, '441'] True True 68 16384 274.9611272600014
169 aime26_6 9 441 [26, '26'] True False 68 16384 288.65659015998244
170 aime26_6 7 441 [26, '26'] True False 68 16384 297.4955001079943
171 aime26_6 3 441 [-0.400000000000000, '-0.4'] True False 68 16384 304.8267116150819
172 aime26_6 8 441 [26, '26'] True False 68 16384 295.7286849679658
173 aime26_6 10 441 [26, '26'] True False 68 16384 292.8044942080742
174 aime26_6 17 441 [16, '16'] True False 68 16384 279.9178612360265
175 aime26_6 6 441 [441, '441'] True True 68 16384 304.5307096239412
176 aime26_6 27 441 [441, '441'] True True 68 16384 264.35084101196844
177 aime26_5 30 65 [65, '65'] True True 152 16384 321.6101568969898
178 aime26_6 14 441 [441, '441'] True True 68 16384 289.6423368930118
179 aime26_6 30 441 [441, '441'] True True 68 16384 262.75079676602036
180 aime26_6 22 441 [2, '2'] True False 68 16384 275.2806919880677
181 aime26_6 4 441 [441, '441'] True True 68 16384 311.8565369140124
182 aime26_6 16 441 [18081, '18081'] True False 68 16384 286.97725864103995
183 aime26_6 20 441 [1, '1'] True False 68 16384 282.4508435910102
184 aime26_7 3 396 [145, '145'] True False 83 16384 265.0680449119536
185 aime26_6 31 441 [1/20, '1 / 20'] True False 68 16384 269.33968355692923
186 aime26_6 21 441 [2026, '2026'] True False 68 16384 283.8166032480076
187 aime26_6 13 441 [26, '26'] True False 68 16384 301.3187062960351
188 aime26_7 7 396 [145, '145'] True False 83 16384 267.2090685790172
189 aime26_7 4 396 [1, '1'] True False 83 16384 270.0965168320108
190 aime26_7 21 396 [6, '6'] True False 83 16384 261.23715727205854
191 aime26_5 24 65 ['0).'] True False 152 16384 357.5881059949752
192 aime26_6 23 441 [441, '441'] True True 68 16384 285.3934911999386
193 aime26_6 26 441 [26, '26'] True False 68 16384 281.25765663490165
194 aime26_5 28 65 [16/9.0, '16/9.'] True False 152 16384 338.9146829160163
195 aime26_6 24 441 [441, '441'] True True 68 16384 285.4074419440003
196 aime26_6 28 441 [20.4200000000000, '20.42'] True False 68 16384 285.37431196693797
197 aime26_7 6 396 [144, '144'] True False 83 16384 279.71426997403614
198 aime26_6 25 441 [441, '441'] True True 68 16384 291.8047097789822
199 aime26_7 1 396 [176, '176'] True False 83 16384 285.76536077295896
200 aime26_7 2 396 [145, '145'] True False 83 16384 290.1915022949688
201 aime26_7 19 396 [144, '144'] True False 83 16384 284.8910701900022
202 aime26_7 23 396 [144, '144'] True False 83 16384 281.5582423929591
203 aime26_7 11 396 [1, '1'] True False 83 16384 298.63355440902524
204 aime26_7 27 396 [1, '1'] True False 83 16384 289.84708561503794
205 aime26_7 26 396 [144, '144'] True False 83 16384 302.87250807799865
206 aime26_7 22 396 [1, '1'] True False 83 16384 312.49028898600955
207 aime26_7 8 396 [144, '144'] True False 83 16384 329.642205556971
208 aime26_8 2 244 [244, '244'] True True 72 16384 297.256799660041
209 aime26_7 24 396 [145, '145'] True False 83 16384 341.3571004800033
210 aime26_7 20 396 [144, '144'] True False 83 16384 348.9899097359739
211 aime26_7 14 396 [145, '145'] True False 83 16384 352.4944593970431
212 aime26_7 9 396 [120, '120'] True False 83 16384 354.99406649102457
213 aime26_7 15 396 [2, '2'] True False 83 16384 356.4706223240355
214 aime26_7 0 396 [289, '289'] True False 83 16384 369.6006611729972
215 aime26_8 10 244 [244, '244'] True True 72 16384 263.29919046803843
216 aime26_7 13 396 [144, '144'] True False 83 16384 371.6238659910159
217 aime26_9 6 29 [6, '6'] True False 192 16384 198.31673118995968
218 aime26_9 11 29 [6, '6'] True False 192 16384 191.23512401198968
219 aime26_7 16 396 [720, '720'] True False 83 16384 379.7711994389538
220 aime26_7 12 396 [144, '144'] True False 83 16384 383.3182889439631
221 aime26_9 4 29 [2, '2'] True False 192 16384 216.66299774695653
222 aime26_7 5 396 [288, '288'] True False 83 16384 390.3024701549439
223 aime26_7 31 396 [145, '145'] True False 83 16384 352.66573005297687
224 aime26_9 3 29 [4, '4'] True False 192 16384 223.04878987499978
225 aime26_8 11 244 [0, '0'] True False 72 16384 291.25984998000786
226 aime26_7 25 396 [145, '145'] True False 83 16384 380.7551164450124
227 aime26_7 29 396 [1, '1'] True False 83 16384 364.89851499104407
228 aime26_9 5 29 [2, '2'] True False 192 16384 221.63837249204516
229 aime26_9 2 29 [3, '3'] True False 192 16384 231.5467264619656
230 aime26_8 0 244 [916, '916'] True False 72 16384 361.2043145070784
231 aime26_9 7 29 [2, '2'] True False 192 16384 221.6332370940363
232 aime26_9 21 29 [6, '6'] True False 192 16384 186.7255224030232
233 aime26_9 23 29 [6, '6'] True False 192 16384 189.6964667410357
234 aime26_8 4 244 [810, '810'] True False 72 16384 339.37614776496775
235 aime26_8 25 244 [0, '0'] True False 72 16384 269.86384164495394
236 aime26_8 23 244 [9, '9'] True False 72 16384 277.6189189259894
237 aime26_9 18 29 [2, '2'] True False 192 16384 206.9695194249507
238 aime26_8 3 244 [244, '244'] True True 72 16384 370.1650946880691
239 aime26_7 17 396 [186, '186'] True False 83 16384 418.8567254350055
240 aime26_8 28 244 [916, '916'] True False 72 16384 266.43057597090956
241 aime26_8 5 244 [392, '392'] True False 72 16384 346.8135666429298
242 aime26_9 14 29 [1, '1'] True False 192 16384 229.950331059983
243 aime26_9 8 29 [2, '2'] True False 192 16384 241.84489837498404
244 aime26_7 10 396 [265, '265'] True False 83 16384 424.9000539970584
245 aime26_8 15 244 [288, '288'] True False 72 16384 308.46706134302076
246 aime26_9 9 29 [2, '2'] True False 192 16384 243.9275676680263
247 aime26_7 18 396 [175, '175'] True False 83 16384 430.88447471300606
248 aime26_8 7 244 [1296, '1296'] True False 72 16384 348.1019606780028
249 aime26_8 8 244 [392, '392'] True False 72 16384 346.29379061597865
250 aime26_9 30 29 [2, '2'] True False 192 16384 209.28173514502123
251 aime26_7 28 396 [144, '144'] True False 83 16384 409.2050212790491
252 aime26_9 15 29 [3, '3'] True False 192 16384 240.6167516990099
253 aime26_9 26 29 [6, '6'] True False 192 16384 213.8559017139487
254 aime26_9 22 29 [2, '2'] True False 192 16384 221.51579072605819
255 aime26_8 6 244 [12, '12'] True False 72 16384 363.6257795689162
256 aime26_8 19 244 [2, '2'] True False 72 16384 310.9007001189748
257 aime26_9 17 29 [2, '2'] True False 192 16384 240.85382933006622
258 aime26_9 29 29 [6, '6'] True False 192 16384 217.73675071401522
259 aime26_7 30 396 [144, '144'] True False 83 16384 406.54220191796776
260 aime26_9 12 29 [2, '2'] True False 192 16384 257.343769179075
261 aime26_8 1 244 [832, '832'] True False 72 16384 401.1092713329708
262 aime26_8 12 244 [81, '81'] True False 72 16384 347.0412950719474
263 aime26_9 13 29 [3, '3'] True False 192 16384 259.76377470896114
264 aime26_8 22 244 [0, '0'] True False 72 16384 319.37727880396415
265 aime26_8 13 244 [916, '916'] True False 72 16384 350.36329651996493
266 aime26_9 20 29 [6, '6'] True False 192 16384 248.5885623630602
267 aime26_9 31 29 [6, '6'] True False 192 16384 231.01300975703634
268 aime26_8 30 244 [162, '162'] True False 72 16384 302.8673607399687
269 aime26_10 15 156 [90, '90'] True False 120 16384 208.55256121209823
270 aime26_8 16 244 [162, '162'] True False 72 16384 345.39930093090516
271 aime26_8 27 244 [458, '458'] True False 72 16384 313.8198327800492
272 aime26_8 20 244 [160, '160'] True False 72 16384 335.0499245818937
273 aime26_8 21 244 [244, '244'] True True 72 16384 332.6422999060014
274 aime26_8 26 244 [458, '458'] True False 72 16384 319.3869919740828
275 aime26_9 0 29 [6, '6'] True False 192 16384 306.09978171100374
276 aime26_8 31 244 [992, '992'] True False 72 16384 310.6315540210344
277 aime26_8 9 244 [0, '0'] True False 72 16384 375.2215174839366
278 aime26_8 18 244 [103, '103'] True False 72 16384 352.0987747410545
279 aime26_9 19 29 [5/2187.0, '5 / 2187. \n'] True False 192 16384 267.90877125097904
280 aime26_8 29 244 [488, '488'] True False 72 16384 322.20636943995487
281 aime26_9 16 29 [1, '1'] True False 192 16384 288.81408902909607
282 aime26_9 10 29 [6, '6'] True False 192 16384 304.0382817189675
283 aime26_9 1 29 [2, '2'] True False 192 16384 327.5026161270216
284 aime26_9 28 29 [2, '2'] True False 192 16384 270.12404160993174
285 aime26_8 17 244 [162, '162'] True False 72 16384 377.37112374196295
286 aime26_8 14 244 [244, '244'] True True 72 16384 386.4450833259616
287 aime26_9 27 29 [3, '3'] True False 192 16384 273.29587970103603
288 aime26_10 18 156 [4, '4'] True False 120 16384 246.10771127103362
289 aime26_9 25 29 [6, '6'] True False 192 16384 288.2122847089777
290 aime26_10 2 156 [135, '135'] True False 120 16384 280.267433178029
291 aime26_8 24 244 [1, '1'] True False 72 16384 381.5664451010525
292 aime26_10 11 156 [-23, '-23'] True False 120 16384 276.411418036907
293 aime26_10 13 156 [14, '14'] True False 120 16384 275.2011213309597
294 aime26_10 3 156 [603/40, '603/40'] True False 120 16384 299.76440358092077
295 aime26_10 7 156 ['1.4 + '] True False 120 16384 295.7335444689961
296 aime26_9 24 29 [1, '1'] True False 192 16384 319.37895233300515
297 aime26_10 31 156 [90, '90'] True False 120 16384 271.9019882749999
298 aime26_10 5 156 ['89/8). \n'] True False 120 16384 298.1490148539888
299 aime26_10 6 156 [-1, '-1'] True False 120 16383 308.1066521749599
300 aime26_11 7 896 [1, '1'] True False 172 16384 268.1387032730272
301 aime26_10 0 156 ['(35/2)(-'] True False 120 16384 322.3596027479507
302 aime26_10 4 156 ['(-9)(3/5) + (15/4)(4/5) + 33/8\n\n'] True False 120 16384 319.7129112279508
303 aime26_10 19 156 [1089, '1089'] True False 120 16384 304.2258708620211
304 aime26_11 3 896 [64 - 1*6, '64 - 6'] True False 172 16384 288.7387018529698
305 aime26_10 10 156 ['-4225*56 - 4225*'] True False 120 16384 325.4656512719812
306 aime26_10 12 156 [160, '160'] True False 120 16384 325.9069039740134
307 aime26_10 17 156 [-7/3.0, '-7/3.\n'] True False 120 16384 323.63646447099745
308 aime26_10 14 156 [-56/33.0, '-56/33. \n'] True False 120 16384 333.3260841059964
309 aime26_12 7 161 [2, '2'] True False 196 16384 178.93453455297276
310 aime26_10 21 156 [521, '521'] True False 120 16384 328.7404847739963
311 aime26_11 12 896 [1, '1'] True False 172 16384 269.60579137702007
312 aime26_10 27 156 ['-33/8).\n'] True False 120 16384 327.92567154194694
313 aime26_10 23 156 ['33/8).'] True False 120 16384 339.3038604820613
314 aime26_11 28 896 [56, '56'] True False 172 16384 215.54940424393862
315 aime26_10 1 156 [5.02500000000000, '5.025'] True False 120 16384 370.2253220070852
316 aime26_11 18 896 [7, '7'] True False 172 16384 253.879476854112
317 aime26_11 15 896 [0, '0'] True False 172 16384 256.2835035499884
318 aime26_10 22 156 [90, '90'] True False 120 16384 348.5618194519775
319 aime26_11 29 896 [64, '64'] True False 172 16384 220.5628901369637
320 aime26_11 14 896 [63, '63'] True False 172 16384 269.4031818700023
321 aime26_11 22 896 [2, '2'] True False 172 16384 245.50000791996717
322 aime26_10 9 156 ['0.8).'] True False 120 16383 374.67650265898556
323 aime26_10 20 156 ['33/8).'] True False 120 16384 365.8481827030191
324 aime26_11 5 896 ['(3). (1)'] True False 172 16384 346.03782451094594
325 aime26_10 26 156 [0, '0'] True False 120 16384 362.5769248730503
326 aime26_10 8 156 [1/2, '1/2'] True False 120 16384 387.6053151950473
327 aime26_10 28 156 [13.8750000000000, '13.875'] True False 120 16384 369.6759151640581
328 aime26_11 13 896 [1, '1'] True False 172 16384 316.06280291092116
329 aime26_10 30 156 [156, '156'] True True 120 16384 375.81433411396574
330 aime26_10 29 156 [1521/1531.0, '1521/1531.'] True False 120 16384 381.1568872999633
331 aime26_11 11 896 [64, '64'] True False 172 16384 338.44366289197933
332 aime26_10 16 156 [12, '12'] True False 120 16384 405.3018175640609
333 aime26_10 25 156 ['33/(1'] True False 120 16384 398.5649297890486
334 aime26_11 2 896 [6, '6'] True False 172 16384 389.0639778659679
335 aime26_10 24 156 [12, '12'] True False 120 16384 402.2364356010221
336 aime26_11 10 896 [64, '64'] True False 172 16384 374.77945253497455
337 aime26_11 1 896 [4, '4'] True False 172 16384 417.2937054251088
338 aime26_11 8 896 [63, '63'] True False 172 16384 398.7829933320172
339 aime26_12 5 161 [2, '2'] True False 196 16384 286.27793643891346
340 aime26_11 6 896 [63, '63'] True False 172 16384 405.26738215307705
341 aime26_11 27 896 [256, '256'] True False 172 16384 308.50421167106833
342 aime26_11 23 896 [10, '10'] True False 172 16384 319.76813179510646
343 aime26_11 4 896 [7, '7'] True False 172 16384 417.4820209930185
344 aime26_12 4 161 [0, '0'] True False 196 16384 296.7784244400682
345 aime26_12 15 161 [44/1, '44/1'] True False 196 16384 288.8533034280408
346 aime26_11 0 896 [1, '1'] True False 172 16384 440.25967135303654
347 aime26_11 31 896 [63, '63'] True False 172 16384 316.6869206869742
348 aime26_12 10 161 [8, '8'] True False 196 16384 297.4066598250065
349 aime26_12 23 161 [4, '4'] True False 196 16384 282.4203065530164
350 aime26_11 19 896 [8, '8'] True False 172 16384 363.7781490900088
351 aime26_12 31 161 [1, '1'] True False 196 16384 278.65476883901283
352 aime26_12 3 161 [4, '4'] True False 196 16384 321.7746555809863
353 aime26_11 20 896 [252, '252'] True False 172 16384 358.92994763096794
354 aime26_11 16 896 [5760, '5760'] True False 172 16384 371.70736664696597
355 aime26_12 12 161 [3, '3'] True False 196 16384 309.07561751792673
356 aime26_13 15 39 [502, '502'] True False 190 16384 265.7713951750193
357 aime26_12 14 161 [0, '0'] True False 196 16384 313.4196494369535
358 aime26_13 7 39 [0, '0'] True False 190 16384 275.6535160141066
359 aime26_12 2 161 [6, '6'] True False 196 16384 339.60977226810064
360 aime26_12 6 161 [62, '62'] True False 196 16383 339.23010652908124
361 aime26_11 25 896 [8, '8'] True False 172 16384 364.8820165611105
362 aime26_12 21 161 [-16/13, '-16/13'] True False 196 16384 312.1724656189326
363 aime26_12 11 161 [4, '4'] True False 196 16384 331.5131335289916
364 aime26_12 8 161 [42/13, '42/13'] True False 196 16384 336.217902706936
365 aime26_12 13 161 [0.000434400000000000, '0.0004344'] True False 196 16384 328.7295371640939
366 aime26_13 11 39 ['(1/502) * 10000 *'] True False 190 16384 287.4105643519433
367 aime26_11 9 896 [1, '1'] True False 172 16384 453.4145278109936
368 aime26_11 21 896 [-1, '-1'] True False 172 16384 392.2047894130228
369 aime26_12 17 161 [0.933000000000000, '0.933'] True False 196 16384 334.5775631070137
370 aime26_12 26 161 [2, '2'] True False 196 16384 322.79107444395777
371 aime26_13 2 39 [2, '2'] True False 190 16384 314.2715831800597
372 aime26_12 20 161 [3, '3'] True False 196 16384 336.3852410999825
373 aime26_11 26 896 [196/2, '196 / 2'] True False 172 16381 379.83791958296206
374 aime26_12 1 161 ['124/39 +'] True False 196 16384 366.19521892094053
375 aime26_12 18 161 ['0).'] True False 196 16384 340.49405911308713
376 aime26_12 29 161 [3, '3'] True False 196 16384 324.73138904804364
377 aime26_12 16 161 ['(34/1'] True False 196 16384 346.1644895209465
378 aime26_11 24 896 [2, '2'] True False 172 16384 391.4470455229748
379 aime26_11 17 896 [64, '64'] True False 172 16384 417.07063584495336
380 aime26_12 19 161 [3, '3'] True False 196 16384 345.8206261449959
381 aime26_13 3 39 [503, '503'] True False 190 16384 326.96142328798305
382 aime26_12 0 161 [39, '39'] True False 196 16384 380.6939633570146
383 aime26_12 30 161 [0, '0'] True False 196 16384 334.64006177301053
384 aime26_13 23 39 [0, '0'] True False 190 16384 294.0929686889285
385 aime26_13 21 39 [0, '0'] True False 190 16384 302.88382985198405
386 aime26_13 4 39 [0, '0'] True False 190 16384 336.92840648896527
387 aime26_12 27 161 [0, '0'] True False 196 16384 356.4503721470246
388 aime26_13 5 39 [0, '0'] True False 190 16384 343.84724998800084
389 aime26_11 30 896 [8, '8'] True False 172 16384 403.819061758928
390 aime26_12 9 161 [0, '0'] True False 196 16384 388.4950877999654
391 aime26_13 6 39 [502, '502'] True False 190 16384 346.319295070949
392 aime26_13 18 39 [1, '1'] True False 190 16384 336.68054211197887
393 aime26_13 12 39 [0, '0'] True False 190 16384 349.18500210298225
394 aime26_13 10 39 [0, '0'] True False 190 16384 349.97793437191285
395 aime26_12 28 161 [117, '117'] True False 196 16384 374.25811822200194
396 aime26_12 22 161 [0, '0'] True False 196 16384 380.6374352009734
397 aime26_12 25 161 [156, '156'] True False 196 16384 378.68654671194963
398 aime26_13 31 39 [0, '0'] True False 190 16384 304.9473666999256
399 aime26_12 24 161 [0, '0'] True False 196 16384 380.6604241040768
400 aime26_13 0 39 [0, '0'] True False 190 16384 372.3395297219977
401 aime26_14 14 681 [1, '1'] True False 107 16384 259.23285224905703
402 aime26_13 13 39 [503, '503'] True False 190 16384 362.75423265399877
403 aime26_13 27 39 [40, '40'] True False 190 16384 340.6071197279962
404 aime26_13 17 39 [1, '1'] True False 190 16384 368.7414992569247
405 aime26_14 21 681 [1, '1'] True False 107 16384 249.5323887130944
406 aime26_13 1 39 [0, '0'] True False 190 16384 398.62394552805927
407 aime26_13 19 39 [0, '0'] True False 190 16384 372.0222592500504
408 aime26_14 7 681 [308, '308'] True False 107 16383 304.26282147003803
409 aime26_13 14 39 [2, '2'] True False 190 16384 380.53606919304
410 aime26_14 12 681 [3, '3'] True False 107 16384 289.0577373689739
411 aime26_13 20 39 [0, '0'] True False 190 16384 375.7042971950723
412 aime26_13 8 39 [11, '11'] True False 190 16383 394.60590776696336
413 aime26_13 26 39 [58, '58'] True False 190 16384 361.9241863399511
414 aime26_13 29 39 [9766, '9766'] True False 190 16384 366.7879649749957
415 aime26_13 9 39 [503, '503'] True False 190 16384 403.64599277998786
416 aime26_14 19 681 [1, '1'] True False 107 16384 288.71703306399286
417 aime26_14 5 681 [1/2, '1/2'] True False 107 16384 340.66435339697637
418 aime26_13 28 39 [0, '0'] True False 190 16384 386.0049958860036
419 aime26_13 22 39 [5, '5'] True False 190 16384 403.3914430590812
420 aime26_14 29 681 [3, '3'] True False 107 16384 281.38201325794216
421 aime26_14 11 681 [2, '2'] True False 107 16384 339.09332119009923
422 aime26_13 30 39 [502, '502'] True False 190 16384 396.7957950759446
423 aime26_14 15 681 [400, '400'] True False 107 16384 326.3138860450126
424 aime26_14 3 681 [1540, '1540'] True False 107 16384 376.18477640103083
425 aime26_14 23 681 [2, '2'] True False 107 16384 303.2593154379865
426 aime26_14 22 681 [2, '2'] True False 107 16384 315.79268273699563
427 aime26_14 6 681 [2, '2'] True False 107 16384 374.1686203009449
428 aime26_14 4 681 [2.61800000000000, '2.618'] True False 107 16384 386.6405701749027
429 aime26_14 26 681 ['1)/'] True False 107 16384 323.2896898930194
430 aime26_14 10 681 [-290, '-290'] True False 107 16384 377.70615759899374
431 aime26_14 13 681 [72, '72'] True False 107 16384 373.94181904301513
432 aime26_15 23 83 [2, '2'] True False 265 16384 233.23109149199445
433 aime26_13 25 39 [501, '501'] True False 190 16384 456.6857058129972
434 aime26_13 16 39 [1, '1'] True False 190 16384 481.9078028360382
435 aime26_13 24 39 [0, '0'] True False 190 16384 466.775175562012
436 aime26_14 18 681 [308, '308'] True False 107 16384 367.90115797903854
437 aime26_14 0 681 [0, '-0'] True False 107 16384 444.30647348205093
438 aime26_14 2 681 [2, '2'] True False 107 16384 436.8336673909798
439 aime26_14 30 681 [4, '4'] True False 107 16384 349.44176964391954
440 aime26_14 1 681 [5, '5'] True False 107 16384 444.66639669588767
441 aime26_16 23 178 [178, '178'] True True 58 16384 205.62018690700643
442 aime26_14 8 681 ['1)/4 * 2'] True False 107 16384 436.8957840380026
443 aime26_16 2 178 [178, '178'] True True 58 16384 247.3203694249969
444 aime26_14 20 681 [800, '800'] True False 107 16384 391.33323896001093
445 aime26_15 13 83 [5, '5'] True False 265 16384 315.4672626539832
446 aime26_16 15 178 [178, '178'] True True 58 16384 222.4876748219831
447 aime26_14 31 681 ['2-4). \n'] True False 107 16383 364.06184034398757
448 aime26_15 7 83 [5, '5'] True False 265 16384 336.5160237309756
449 aime26_16 7 178 [178, '178'] True True 58 16384 236.30408048001118
450 aime26_14 17 681 [800, '800'] True False 107 16384 404.13785703200847
451 aime26_16 3 178 [178, '178'] True True 58 16384 252.0510226849001
452 aime26_14 27 681 [2, '2'] True False 107 16384 377.5783157279948
453 aime26_14 16 681 [-184, '-184'] True False 107 16384 413.71698021900374
454 aime26_15 28 83 [12, '12'] True False 265 16384 273.2774544240674
455 aime26_16 13 178 [178, '178'] True True 58 16384 242.87935466703493
456 aime26_16 31 178 [178, '178'] True True 58 16384 214.3180837359978
457 aime26_16 4 178 [178, '178'] True True 58 16384 263.27735008404125
458 aime26_14 28 681 [2, '2'] True False 107 16384 394.97043026890606
459 aime26_15 26 83 [10, '10'] True False 265 16384 292.81422881700564
460 aime26_15 5 83 [2, '2'] True False 265 16384 370.3800397469895
461 aime26_16 10 178 [178, '178'] True True 58 16384 266.1407008350361
462 aime26_15 15 83 [5, '5'] True False 265 16384 325.75354475108907
463 aime26_16 0 178 [178, '178'] True True 58 16384 294.52419706701767
464 aime26_14 9 681 [2, '2'] True False 107 16384 469.6250059240265
465 aime26_14 24 681 [108, '108'] True False 107 16384 418.3549683870515
466 aime26_17 7 243 [10, '10'] True False 369 16384 209.10605586494785
467 aime26_16 18 178 [178, '178'] True True 58 16384 260.63941483199596
468 aime26_15 2 83 [21, '21'] True False 265 16384 401.83065118792
469 aime26_16 19 178 [178, '178'] True True 58 16384 267.7884453299921
470 aime26_15 6 83 [2, '2'] True False 265 16384 388.08377294708043
471 aime26_17 5 243 [1, '1'] True False 369 16384 232.70200040598866
472 aime26_16 20 178 [178, '178'] True True 58 16384 271.8096692559775
473 aime26_16 26 178 [178, '178'] True True 58 16384 264.59788184496574
474 aime26_15 3 83 [1, '1'] True False 265 16384 408.6881536919391
475 aime26_16 12 178 [178, '178'] True True 58 16384 287.00025533302687
476 aime26_15 31 83 [10, '10'] True False 265 16384 316.8658384840237
477 aime26_16 14 178 [178, '178'] True True 58 16384 283.21151920000557
478 aime26_16 9 178 [-2, '-2'] True False 58 16384 293.5685303249629
479 aime26_16 5 178 [24, '24'] True False 58 16384 303.27532372495625
480 aime26_15 12 83 [5, '5'] True False 265 16388 379.5600662960205
481 aime26_16 6 178 [178, '178'] True True 58 16384 301.0462891180068
482 aime26_15 22 83 [5, '5'] True False 265 16384 346.7132376029622
483 aime26_15 10 83 [120, '120'] True False 265 16384 384.6827885339735
484 aime26_16 21 178 [178, '178'] True True 58 16384 280.4042428539833
485 aime26_14 25 681 [2, '2'] True False 107 16384 446.1858595380327
486 aime26_15 20 83 [21, '21'] True False 265 16384 358.0112816769397
487 aime26_15 4 83 [2, '2'] True False 265 16384 423.0209839390591
488 aime26_16 27 178 [178, '178'] True True 58 16384 282.144441050943
489 aime26_15 14 83 [2, '2'] True False 265 16384 377.8026919440599
490 aime26_15 21 83 [5, '5'] True False 265 16384 365.6220587049611
491 aime26_16 29 178 [178, '178'] True True 58 16384 289.04695653996896
492 aime26_16 11 178 [165, '165'] True False 58 16384 317.08520313201007
493 aime26_15 29 83 [5, '5'] True False 265 16384 347.39833492506295
494 aime26_15 19 83 [1, '1'] True False 265 16384 374.4522898889845
495 aime26_15 18 83 [5, '5'] True False 265 16384 382.6047315290198
496 aime26_16 8 178 [178, '178'] True True 58 16384 329.38757130294107
497 aime26_15 11 83 [12, '12'] True False 265 16384 411.8613644379657
498 aime26_16 30 178 [178, '178'] True True 58 16384 295.6823500250466
499 aime26_16 28 178 [178, '178'] True True 58 16384 300.8178362289909
500 aime26_16 16 178 [32, '32'] True False 58 16384 318.7794563550269
501 aime26_17 31 243 ['0).'] True False 369 16384 204.90040430100635
502 aime26_16 17 178 [178, '178'] True True 58 16384 325.12364382704254
503 aime26_15 0 83 [5, '5'] True False 265 16384 463.8715728119714
504 aime26_15 9 83 [2, '2'] True False 265 16384 429.1758108129725
505 aime26_15 8 83 [1, '1'] True False 265 16384 444.3228299950715
506 aime26_15 30 83 [100, '100'] True False 265 16384 372.06599287095014
507 aime26_15 27 83 [4, '4'] True False 265 16384 379.9468840090558
508 aime26_15 1 83 [126, '126'] True False 265 16384 475.7266066179145
509 aime26_16 22 178 [178, '178'] True True 58 16384 335.24523014295846
510 aime26_15 16 83 [6, '6'] True False 265 16384 412.6573353239801
511 aime26_17 26 243 [1, '1'] True False 369 16384 248.2532445479883
512 aime26_17 23 243 [10, '10'] True False 369 16384 260.9219120760681
513 aime26_16 1 178 [178, '178'] True True 58 16384 380.9064975139918
514 aime26_15 17 83 [4, '4'] True False 265 16384 422.233889504103
515 aime26_17 3 243 [1, '1'] True False 369 16384 315.5343959949678
516 aime26_15 25 83 [1, '1'] True False 265 16384 410.5522578150267
517 aime26_17 27 243 [10, '10'] True False 369 16384 265.9303741049953
518 aime26_15 24 83 [10, '10'] True False 265 16384 414.30071893602144
519 aime26_17 1 243 [1, '1'] True False 369 16384 331.1239894530736
520 aime26_17 13 243 [362880, '362880'] True False 369 16384 332.30457129806746
521 aime26_16 25 178 [178, '178'] True True 58 16384 379.59483606694266
522 aime26_17 22 243 [sqrt(11), '\\sqrt{11}'] True False 369 16384 308.86588410299737
523 aime26_17 18 243 [9, '9'] True False 369 16384 316.05851335602347
524 aime26_17 24 243 [10, '10'] True False 369 16384 316.29409562807996
525 aime26_17 15 243 [2, '2'] True False 369 16384 337.76417696790304
526 aime26_18 10 503 [0, '0'] True False 150 16384 245.30731063499115
527 aime26_17 4 243 [10, '10'] True False 369 16384 369.9160043710144
528 aime26_18 31 503 [45, '45'] True False 150 16384 190.59555449697655
529 aime26_17 11 243 [2, '2'] True False 369 16384 358.6783873740351
530 aime26_17 6 243 [11, '11'] True False 369 16384 373.0730599020608
531 aime26_17 19 243 [10, '10'] True False 369 16384 340.7387321740389
532 aime26_17 2 243 [430, '430'] True False 369 16384 390.6090245679952
533 aime26_17 21 243 [1, '1'] True False 369 16384 344.8900457409909
534 aime26_16 24 178 [178, '178'] True True 58 16384 441.1594640830299
535 aime26_17 14 243 [0, '0'] True False 369 16384 394.21008377696853
536 aime26_18 7 503 [126, '126'] True False 150 16384 310.2969554460142
537 aime26_17 10 243 [2, '2'] True False 369 16384 413.8905827529961
538 aime26_19 2 279 [2, '2'] True False 143 16384 245.4408885409357
539 aime26_18 15 503 [2022, '2022'] True False 150 16384 284.9995242799632
540 aime26_17 29 243 [11, '11'] True False 369 16384 371.1116032419959
541 aime26_17 9 243 [sqrt(11), '\\sqrt{11}'] True False 369 16384 429.4266384630464
542 aime26_18 5 503 [10, '10'] True False 150 16384 343.7767961079953
543 aime26_17 0 243 [10, '10'] True False 369 16384 460.6853696509497
544 aime26_17 17 243 [1, '1'] True False 369 16384 410.3506849500118
545 aime26_18 2 503 [1, '1'] True False 150 16384 355.316159440903
546 aime26_19 15 279 [58, '58'] True False 143 16384 230.16082769806962
547 aime26_20 2 190 [2, '2'] True False 105 16385 206.26670655200724
548 aime26_17 8 243 ['1). \n'] True False 369 16384 445.0477843990084
549 aime26_17 12 243 [11, '11'] True False 369 16384 444.8906507890206
550 aime26_17 20 243 [sqrt(10), '\\sqrt{10}'] True False 369 16384 421.06428736797534
551 aime26_18 4 503 [28, '28'] True False 150 16384 369.09983424306847
552 aime26_18 3 503 [1, '1'] True False 150 16384 373.1530039400095
553 aime26_18 23 503 [45, '45'] True False 150 16384 295.64824117789976
554 aime26_17 30 243 [11, '11'] True False 369 16384 396.90061193401925
555 aime26_18 13 503 [128*19, '128*(19)'] True False 150 16384 338.1938798810588
556 aime26_19 7 279 [7, '7'] True False 143 16384 277.6934892440913
557 aime26_18 6 503 [2, '2'] True False 150 16384 375.09152839693706
558 aime26_18 18 503 ['20)^2'] True False 150 16384 323.6613525720313
559 aime26_19 10 279 [9, '9'] True False 143 16384 277.215089141042
560 aime26_18 11 503 [1009, '1009'] True False 150 16384 353.53251649590675
561 aime26_18 26 503 [12, '12'] True False 150 16384 306.0663401680067
562 aime26_18 14 503 [994, '994'] True False 150 16384 346.7141564260237
563 aime26_18 12 503 [16, '16'] True False 150 16384 363.9250123889651
564 aime26_19 4 279 [72, '72'] True False 143 16384 308.4821824679384
565 aime26_18 21 503 [2, '2'] True False 150 16384 343.19027549400926
566 aime26_20 7 190 [5, '5'] True False 105 16384 246.2372808959335
567 aime26_17 16 243 [252, '252'] True False 369 16384 486.11388579697814
568 aime26_18 1 503 [1, '1'] True False 150 16384 430.17315595201217
569 aime26_19 1 279 [10, '10'] True False 143 16384 329.8499968700344
570 aime26_17 28 243 [factorial(10), '10!'] True False 369 16384 451.611593132955
571 aime26_18 19 503 [-408, '-408'] True False 150 16384 355.25456082692835
572 aime26_20 5 190 [7, '7'] True False 105 16384 262.14850947703235
573 aime26_20 15 190 [190, '190'] True True 105 16384 246.64696872700006
574 aime26_19 6 279 [999, '999'] True False 143 16384 330.541296524927
575 aime26_18 20 503 [180, '180'] True False 150 16384 365.49420865403954
576 aime26_18 28 503 [1600 - 1*160, '1600 - 160'] True False 150 16384 347.86353459290694
577 aime26_19 28 279 [10, '10'] True False 143 16384 289.5738632460125
578 aime26_18 29 503 [196, '196'] True False 150 16384 348.2922443379648
579 aime26_17 25 243 [3, '3'] True False 369 16383 481.1736256350996
580 aime26_19 25 279 [999, '999'] True False 143 16384 299.59965262701735
581 aime26_18 27 503 [2**6*3*5, '2^6 * 3 * 5'] True False 150 16384 356.4992286089109
582 aime26_18 9 503 [2, '2'] True False 150 16384 422.57052237400785
583 aime26_19 22 279 [10, '10'] True False 143 16384 307.65435945708305
584 aime26_19 23 279 [1000, '1000'] True False 143 16384 306.9495285029989
585 aime26_18 8 503 [-2, '-2'] True False 150 16384 433.5438640260836
586 aime26_19 19 279 [999, '999'] True False 143 16384 313.2768622559961
587 aime26_18 22 503 [125, '125'] True False 150 16384 380.0150910129305
588 aime26_18 0 503 [0, '0'] True False 150 16384 462.61269466008525
589 aime26_19 3 279 [9, '9'] True False 143 16384 359.40792947798036
590 aime26_18 30 503 [30, '30'] True False 150 16384 369.4929645799566
591 aime26_20 3 190 [21, '21'] True False 105 16389 300.7922949179774
592 aime26_19 18 279 [9 + 90 + 90, '9 + 90 + 90'] True False 143 16384 329.1443631310249
593 aime26_19 31 279 [999, '999'] True False 143 16384 315.50606699299533
594 aime26_20 10 190 [7, '7'] True False 105 16384 294.7112294610124
595 aime26_20 18 190 [190, '190'] True True 105 16387 283.3077301529702
596 aime26_19 30 279 ['5*8 + '] True False 143 16384 318.5193330720067
597 aime26_19 11 279 [999, '999'] True False 143 16384 349.4360787089681
598 aime26_19 5 279 [0, '0'] True False 143 16384 368.58832269907
599 aime26_20 19 190 [5 - 1*1, '5 - 1'] True False 105 16384 278.211101192981
600 aime26_19 20 279 [9, '9'] True False 143 16384 331.84142891399097
601 aime26_19 12 279 [9, '9'] True False 143 16384 350.12131175608374
602 aime26_18 17 503 [45, '45'] True False 150 16384 413.41671437805053
603 aime26_19 16 279 [999, '999'] True False 143 16384 345.388313716976
604 aime26_20 1 190 [190, '190'] True True 105 16384 326.3690607099561
605 aime26_20 23 190 [190, '190'] True True 105 16384 278.0869281409541
606 aime26_19 14 279 [488, '488'] True False 143 16384 353.58901292295195
607 aime26_19 26 279 [999, '999'] True False 143 16384 339.01860194001347
608 aime26_19 0 279 [990, '990'] True False 143 16384 397.3906103549525
609 aime26_20 31 190 [515, '515'] True False 105 16384 274.3788838200271
610 aime26_20 11 190 [14, '14'] True False 105 16384 314.6991762020625
611 aime26_20 21 190 [190, '190'] True True 105 16386 299.7105921320617
612 aime26_18 16 503 [20, '20'] True False 150 16384 437.9761678460054
613 aime26_19 21 279 [10, '10'] True False 143 16384 356.8219858621014
614 aime26_19 13 279 [1, '1'] True False 143 16384 372.86409916298
615 aime26_20 4 190 [190, '190'] True True 105 16387 338.809226318961
616 aime26_19 27 279 [999, '999'] True False 143 16384 358.4291153390659
617 aime26_18 25 503 ['1/2)(1 +'] True False 150 16384 424.62799170194194
618 aime26_19 29 279 [10, '10'] True False 143 16384 363.0420827160124
619 aime26_20 6 190 [168, '168'] True False 105 16384 350.21932142192964
620 aime26_18 24 503 [3, '3'] True False 150 16384 428.5748416839633
621 aime26_19 8 279 [1100, '1100'] True False 143 16384 406.70749400998466
622 aime26_20 26 190 [16380, '16380'] True False 105 16384 321.74154272302985
623 aime26_21 2 50 [50, '50'] True True 78 16384 299.93390292394906
624 aime26_19 17 279 [1010, '1010'] True False 143 16384 398.3641639020061
625 aime26_19 9 279 [10, '10'] True False 143 16384 416.9989080899395
626 aime26_20 13 190 [-217, '-217'] True False 105 16387 352.402182733058
627 aime26_20 27 190 [16, '16'] True False 105 16384 334.31620356300846
628 aime26_21 15 50 ['41 + 9 +'] True False 78 16384 262.613993027946
629 aime26_21 7 50 [4*sqrt(10), '4\\sqrt{10}'] True False 78 16384 291.44989300204907
630 aime26_20 14 190 [3, '3'] True False 105 16384 367.44100189604796
631 aime26_19 24 279 [999, '999'] True False 143 16384 409.84950627794024
632 aime26_20 8 190 [1465, '1465'] True False 105 16384 384.3626606100006
633 aime26_20 22 190 [6.60000000000000, '6.6'] True False 105 16384 361.66528597299475
634 aime26_20 0 190 [190, '190'] True True 105 16384 408.882195202983
635 aime26_21 31 50 [9, '9'] True False 78 16384 210.7323843470076
636 aime26_20 17 190 [190, '190'] True True 105 16386 392.2911203140393
637 aime26_20 29 190 [3, '3'] True False 105 16384 368.5679162570741
638 aime26_21 3 50 [59, '59'] True False 78 16384 350.6558081379626
639 aime26_22 4 754 ['6).'] True False 127 16384 211.48123246000614
640 aime26_20 30 190 [637560, '637560'] True False 105 16384 372.92703375802375
641 aime26_21 23 50 [41, '41'] True False 78 16384 253.0972562659299
642 aime26_20 16 190 [190, '190'] True True 105 16384 406.41751364804804
643 aime26_20 9 190 [190, '190'] True True 105 16384 418.44865975005087
644 aime26_21 10 50 [12, '12'] True False 78 16384 324.91871382202953
645 aime26_20 24 190 [190, '190'] True True 105 16384 393.9604027699679
646 aime26_21 18 50 [78, '78'] True False 78 16384 319.8047055740608
647 aime26_20 28 190 [10, '10'] True False 105 16384 413.7923369319178
648 aime26_22 15 754 [6, '6'] True False 127 16384 229.52608763298485
649 aime26_22 3 754 [6, '6'] True False 127 16384 261.2356324469438
650 aime26_21 26 50 [9, '9'] True False 78 16384 287.5125441250857
651 aime26_22 5 754 ['(1/3'] True False 127 16384 258.0018143609632
652 aime26_22 12 754 [6, '6'] True False 127 16384 248.80596434499603
653 aime26_21 6 50 [9, '9'] True False 78 16384 377.96133780502714
654 aime26_22 2 754 [2/(3*(1 - 4/9)**2), '(2/3) / (1 - (4/9))^2'] True False 127 16384 270.4477697870461
655 aime26_20 20 190 [1225/3432, '1225 / 3432'] True False 105 16385 446.19608742103446
656 aime26_22 11 754 [6, '6'] True False 127 16384 254.34507943305653
657 aime26_22 1 754 [2, '2'] True False 127 16384 281.1954249930568
658 aime26_22 6 754 [6, '6'] True False 127 16384 265.21796654805075
659 aime26_22 13 754 [6, '6'] True False 127 16384 252.52099832810927
660 aime26_22 14 754 ['2/3). \n'] True False 127 16384 254.66776625195052
661 aime26_20 12 190 [1, '1'] True False 105 16386 469.0507616470568
662 aime26_21 1 50 [sqrt(201), '\\sqrt{201}'] True False 78 16384 427.62554567004554
663 aime26_21 13 50 [41, '41'] True False 78 16384 369.37955417099874
664 aime26_20 25 190 [674/115, '674 / 115'] True False 105 16390 444.9782557069557
665 aime26_21 5 50 [9, '9'] True False 78 16384 417.71124340896495
666 aime26_22 21 754 [1, '1'] True False 127 16384 233.1466475330526
667 aime26_21 29 50 [9, '9'] True False 78 16384 302.9902574690059
668 aime26_21 22 50 [9, '9'] True False 78 16384 335.7458940439392
669 aime26_21 12 50 [41, '41'] True False 78 16384 384.82985955500044
670 aime26_21 11 50 [50, '50'] True True 78 16384 391.363073588931
671 aime26_21 27 50 [59, '59'] True False 78 16384 311.730253997026
672 aime26_21 4 50 [0, '0'] True False 78 16384 432.5539343659766
673 aime26_21 14 50 [18, '18'] True False 78 16384 385.1041150810197
674 aime26_21 17 50 [1681, '1681'] True False 78 16384 390.01395543909166
675 aime26_21 30 50 [50, '50'] True True 78 16384 324.59640388702974
676 aime26_21 19 50 [25600 - 1*268, '25600 - 268'] True False 78 16384 384.7437892490998
677 aime26_21 21 50 [201, '201'] True False 78 16384 365.37375150294974
678 aime26_22 10 754 [829, '829'] True False 127 16384 299.1713194149779
679 aime26_22 31 754 [8/75.0, '8/75. \n'] True False 127 16384 248.5292080710642
680 aime26_22 7 754 [5, '5'] True False 127 16384 308.5836004510056
681 aime26_21 20 50 [50, '50'] True True 78 16384 367.82448118098546
682 aime26_22 29 754 [6, '6'] True False 127 16384 253.8375841040397
683 aime26_21 8 50 [9, '9'] True False 78 16384 428.570697797928
684 aime26_23 7 245 [2, '2'] True False 91 16384 241.52321630797815
685 aime26_23 10 245 [2, '2'] True False 91 16384 239.88808647799306
686 aime26_23 18 245 [1 + 2*600*11, '2*600*11 + 1'] True False 91 16384 226.4554013289744
687 aime26_22 18 754 [4, '4'] True False 127 16384 287.10707725503016
688 aime26_21 28 50 [720, '720'] True False 78 16384 347.8597265910357
689 aime26_21 25 50 [9, '9'] True False 78 16384 358.28263482800685
690 aime26_22 23 754 [17/27.0, '17/27. \n'] True False 127 16384 279.3367207470583
691 aime26_21 9 50 [0, '0'] True False 78 16384 443.1886789170094
692 aime26_22 24 754 [6, '6'] True False 127 16384 291.00432221603114
693 aime26_21 0 50 [41, '41'] True False 78 16384 496.2535247770138
694 aime26_22 27 754 ['3) +'] True False 127 16384 298.3214470440289
695 aime26_21 16 50 [80, '80'] True False 78 16384 444.57889866793994
696 aime26_22 26 754 [1 - 1*4.0, '1-4.'] True False 127 16384 308.9855005580466
697 aime26_23 2 245 [60052, '60052'] True False 91 16384 290.89475323993247
698 aime26_22 19 754 ['1) +'] True False 127 16384 322.01069244008977
699 aime26_22 28 754 [1 - 32/2, '1 - 32/2'] True False 127 16384 301.41204253199976
700 aime26_23 11 245 [2, '2'] True False 91 16384 284.7868493819842
701 aime26_23 4 245 [1, '1'] True False 91 16384 300.2008611980127
702 aime26_21 24 50 [39, '39'] True False 78 16384 407.0160236679949
703 aime26_23 3 245 [2, '2'] True False 91 16384 303.5856904289685
704 aime26_22 17 754 [1, '1'] True False 127 16384 343.98909052298404
705 aime26_23 15 245 [12, '12'] True False 91 16384 283.2538833399303
706 aime26_22 22 754 [409, '409'] True False 127 16384 337.067302228068
707 aime26_23 31 245 [250, '250'] True False 91 16384 268.2960646050051
708 aime26_23 6 245 [25.7000000000000, '25.7'] True False 91 16384 308.9681834100047
709 aime26_22 8 754 [1/3.0, '1/3.'] True False 127 16384 381.0462423119461
710 aime26_24 7 669 [1, '1'] True False 108 16384 257.32992249692325
711 aime26_23 23 245 [2, '2'] True False 91 16382 305.06484266300686
712 aime26_24 15 669 [1, '1'] True False 108 16384 249.61108902993146
713 aime26_23 27 245 [125/6.0, '125/6.'] True False 91 16384 301.14529025007505
714 aime26_23 29 245 [4, '4'] True False 91 16384 297.5818314519711
715 aime26_23 19 245 [2*2, '2*2'] True False 91 16384 315.0355262879748
716 aime26_23 21 245 ['(2.449 + 1.41'] True False 91 16384 314.3555376000004
717 aime26_23 12 245 [6, '6'] True False 91 16384 327.5571242129663
718 aime26_23 26 245 ['(5/2) /'] True False 91 16384 310.51171361503657
719 aime26_24 2 669 [159, '159'] True False 108 16384 294.656453214935
720 aime26_22 20 754 [409, '409'] True False 127 16384 376.95176020404324
721 aime26_23 14 245 [30750, '30750'] True False 91 16384 327.8586186940083
722 aime26_22 30 754 [1/3.0, '1/3.'] True False 127 16384 362.9791588849621
723 aime26_23 5 245 [2, '2'] True False 91 16383 350.218542879913
724 aime26_23 13 245 [6, '6'] True False 91 16384 340.3218289640499
725 aime26_25 2 850 [0, '0'] True False 168 16384 205.62281533703208
726 aime26_22 0 754 [4/81.0, '4/81. \n'] True False 127 16384 442.4225423129974
727 aime26_23 1 245 [1, '1'] True False 91 16384 359.99033316096757
728 aime26_23 9 245 ['(2*5 - '] True False 91 16384 349.2910459539853
729 aime26_24 14 669 [1, '1'] True False 108 16384 273.7254154639086
730 aime26_22 25 754 [404, '404'] True False 127 16384 378.8202398370486
731 aime26_23 22 245 [4, '4'] True False 91 16384 333.39423797803465
732 aime26_24 10 669 [11/90, '11/90'] True False 108 16384 292.6574151760433
733 aime26_22 9 754 [1/6.0, '1/6. \n'] True False 127 16384 432.9347954749828
734 aime26_23 17 245 [2, '2'] True False 91 16384 345.44179236795753
735 aime26_23 0 245 [1, '1'] True False 91 16384 377.8215694470564
736 aime26_24 23 669 [0.1111 - 1*0.001, '0.1111 - 0.00100'] True False 108 16384 258.7262624569703
737 aime26_22 16 754 [4/9.0, '4/9. \n'] True False 127 16384 420.2012946830364
738 aime26_23 20 245 ['1)^'] True False 91 16383 351.0072485530982
739 aime26_23 16 245 [2, '2'] True False 91 16384 357.60044612607453
740 aime26_24 19 669 [1, '1'] True False 108 16384 277.1862872670172
741 aime26_23 30 245 ['2 )\n'] True False 91 16384 339.10205452807713
742 aime26_24 13 669 [10, '10'] True False 108 16384 310.7158418010222
743 aime26_24 3 669 [10**102, '10^102'] True False 108 16384 340.4365843679989
744 aime26_24 31 669 ['1/9 + 1/'] True False 108 16384 251.03937909693923
745 aime26_24 5 669 [81, '81'] True False 108 16384 346.727816308965
746 aime26_24 11 669 [0, '0'] True False 108 16384 329.51496967999265
747 aime26_23 8 245 [5, '5'] True False 91 16384 403.1274079839932
748 aime26_25 7 850 [225, '225'] True False 168 16384 225.38752485706937
749 aime26_24 6 669 ['1/9 +'] True False 108 16384 350.9497591810068
750 aime26_24 18 669 [959, '959'] True False 108 16384 318.66658842994366
751 aime26_24 22 669 [0, '0'] True False 108 16384 309.65769746294245
752 aime26_24 21 669 [11, '11'] True False 108 16384 310.0025919089094
753 aime26_23 28 245 ['1/4 +'] True False 91 16384 383.1176959699951
754 aime26_23 24 245 [125, '125'] True False 91 16384 393.02482702198904
755 aime26_24 9 669 ['1).'] True False 108 16384 360.37931649794336
756 aime26_24 20 669 [0.001 + 0.1212121212, '0.1212121212\n\n+ 0.00100'] True False 108 16384 323.84217543399427
757 aime26_24 26 669 [1, '1'] True False 108 16384 301.0743780309567
758 aime26_24 29 669 [1.00001000000000e-7, '0.000000100001000'] True False 108 16384 293.264414921985
759 aime26_25 4 850 [0, '0'] True False 168 16384 268.9971168859629
760 aime26_24 0 669 ['10/90 - 9/'] True False 108 16384 390.39416054205503
761 aime26_26 7 132 [400, '400'] True False 121 16384 196.34600565594155
762 aime26_24 1 669 [9680, '9680'] True False 108 16384 395.2841258139815
763 aime26_24 4 669 [35, '35'] True False 108 16384 394.70465906895697
764 aime26_23 25 245 ['4 ). \n'] True False 91 16384 419.5996960620396
765 aime26_24 30 669 ['100...000 - 00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000'] True False 108 16384 310.5852227190044
766 aime26_24 12 669 [901, '901'] True False 108 16384 373.3950782819884
767 aime26_24 27 669 [345, '345'] True False 108 16384 330.3165084209759
768 aime26_25 13 850 [13020000, '13020000'] True False 168 16384 274.6318955369061
769 aime26_24 28 669 [-1/999 + 1/9, '1/9 - 1/999'] True False 108 16384 333.7744311679853
770 aime26_24 17 669 ['1/9 + 1/99 + 1/999 + 1/9999 +'] True False 108 16384 377.6195642630337
771 aime26_26 2 132 [400, '400'] True False 121 16384 245.23731272295117
772 aime26_25 10 850 [2, '2'] True False 168 16384 296.4081261019455
773 aime26_24 25 669 [111, '111'] True False 108 16384 364.9745882229181
774 aime26_25 6 850 [64, '64'] True False 168 16384 311.03035184391774
775 aime26_25 1 850 [2, '2'] True False 168 16384 344.3126967009157
776 aime26_25 21 850 [8, '8'] True False 168 16384 295.46186500496697
777 aime26_25 3 850 [5100, '5100'] True False 168 16383 348.4158036389854
778 aime26_25 15 850 [9, '9'] True False 168 16384 305.04654650809243
779 aime26_25 5 850 [8, '8'] True False 168 16384 322.6960337560158
780 aime26_24 8 669 [111, '111'] True False 108 16384 436.822573813959
781 aime26_25 22 850 [140000, '140000'] True False 168 16384 306.6078580680769
782 aime26_25 23 850 [2, '2'] True False 168 16384 308.0894521549344
783 aime26_25 18 850 [0, '0'] True False 168 16384 314.06009827693924
784 aime26_27 2 223 [18, '18'] True False 166 16384 212.84374404896516
785 aime26_25 30 850 [765, '765'] True False 168 16384 307.9859063240001
786 aime26_25 14 850 [595, '595'] True False 168 16384 334.4473948919913
787 aime26_26 5 132 [2, '2'] True False 121 16384 294.3074756839778
788 aime26_25 12 850 ['0).'] True False 168 16384 344.482249559951
789 aime26_25 26 850 [425, '425'] True False 168 16384 322.41304246499203
790 aime26_25 31 850 [225, '225'] True False 168 16384 317.19177402590867
791 aime26_24 24 669 [0, '0'] True False 108 16384 423.428264503018
792 aime26_26 10 132 [346562, '346562'] True False 121 16384 292.328469144064
793 aime26_24 16 669 [0, '0'] True False 108 16384 453.3190098120831
794 aime26_25 11 850 [2, '2'] True False 168 16384 352.4471327490173
795 aime26_25 20 850 [375, '375'] True False 168 16384 344.0237119909143
796 aime26_25 9 850 [0, '0'] True False 168 16384 370.856116447947
797 aime26_26 18 132 [4, '4'] True False 121 16384 293.91506381402723
798 aime26_25 27 850 [36, '36'] True False 168 16384 350.38735675101634
799 aime26_26 3 132 [400, '400'] True False 121 16384 328.9357591769658
800 aime26_25 29 850 [22, '22'] True False 168 16384 351.78513580199797
801 aime26_26 26 132 [1, '1'] True False 121 16383 272.3827625819249
802 aime26_25 19 850 [0, '0'] True False 168 16384 369.1639384099981
803 aime26_25 0 850 [8, '8'] True False 168 16384 426.7061020738911
804 aime26_26 15 132 [2, '2'] True False 121 16384 319.5460303579457
805 aime26_26 17 132 [400, '400'] True False 121 16384 313.18350551708136
806 aime26_26 23 132 [6, '6'] True False 121 16384 288.85337420203723
807 aime26_26 4 132 [2511040.25000000, '2511040.25'] True False 121 16384 344.2576297580963
808 aime26_25 28 850 [2, '2'] True False 168 16384 371.26953098294325
809 aime26_25 16 850 [16, '16'] True False 168 16384 398.0016696980456
810 aime26_26 19 132 [11, '11'] True False 121 16384 329.2378715300001
811 aime26_25 17 850 [85, '85'] True False 168 16384 400.92357789503876
812 aime26_27 7 223 [88.5000000000000, '88.5'] True False 166 16384 268.76789214706514
813 aime26_25 25 850 [2, '2'] True False 168 16384 391.3199982889928
814 aime26_25 8 850 [850, '850'] True True 168 16384 418.86191915592644
815 aime26_26 13 132 [3, '3'] True False 121 16384 356.94788720598444
816 aime26_26 11 132 [400, '400'] True False 121 16384 369.1258072779747
817 aime26_26 31 132 [11, '11'] True False 121 16384 313.0753259359626
818 aime26_27 10 223 [-5, '-5'] True False 166 16384 280.12512652098667
819 aime26_26 14 132 [0, '0'] True False 121 16384 367.38143343897536
820 aime26_26 6 132 [40, '40'] True False 121 16384 380.7845742580248
821 aime26_26 0 132 [400, '400'] True False 121 16384 391.8119989039842
822 aime26_26 21 132 [12, '12'] True False 121 16384 341.4780967690749
823 aime26_27 26 223 [9, '9'] True False 166 16384 268.61445702204946
824 aime26_27 27 223 [1/6, '1/6'] True False 166 16384 263.47624559199903
825 aime26_26 1 132 [0, '0'] True False 121 16384 397.14063037908636
826 aime26_26 29 132 [2, '2'] True False 121 16384 329.1530249520438
827 aime26_26 12 132 [12.6660000000000, '12.666'] True False 121 16384 381.69837557605933
828 aime26_27 18 223 [1, '1'] True False 166 16384 279.94133954902645
829 aime26_27 23 223 [19, '19'] True False 166 16384 282.1705578939291
830 aime26_27 3 223 ['250 - 888/'] True False 166 16384 325.1897300740238
831 aime26_27 15 223 [18, '18'] True False 166 16384 295.15986891894136
832 aime26_25 24 850 [-407.500000000000, '-407.5'] True False 168 16384 435.3003467550734
833 aime26_26 9 132 [2, '2'] True False 121 16384 400.52822423900943
834 aime26_27 11 223 [0, '0'] True False 166 16384 307.2872026358964
835 aime26_26 27 132 [0, '0'] True False 121 16384 348.2330906619318
836 aime26_28 6 107 [1, '1'] True False 147 16384 254.6807672129944
837 aime26_27 31 223 [5, '5'] True False 166 16384 278.93404176901095
838 aime26_26 30 132 [66, '66'] True False 121 16384 347.2150179500459
839 aime26_26 22 132 [3, '3'] True False 121 16384 365.8817514020484
840 aime26_26 20 132 [400, '400'] True False 121 16384 374.3112427009037
841 aime26_27 14 223 [117, '117'] True False 166 16384 314.95804561895784
842 aime26_26 25 132 [-1.75000000000000, '-1.75'] True False 121 16384 373.4584026261
843 aime26_26 8 132 [4, '4'] True False 121 16384 423.0948523900006
844 aime26_27 6 223 [25, '25'] True False 166 16384 337.8629020479275
845 aime26_27 13 223 [33, '33'] True False 166 16384 326.9846119219437
846 aime26_27 5 223 [2, '2'] True False 166 16359 342.8890575240366
847 aime26_26 28 132 [-11.4190000000000, '-11.419'] True False 121 16384 379.0646543140756
848 aime26_27 21 223 ['(20/3 - 45/3)^2 +'] True False 166 16384 323.72146556002554
849 aime26_27 1 223 [1, '1'] True False 166 16384 366.54464890400413
850 aime26_27 4 223 [3, '3'] True False 166 16384 361.90259542304557
851 aime26_27 29 223 ['(13858 - 23'] True False 166 16384 317.4115779439453
852 aime26_26 16 132 [6, '6'] True False 121 16384 431.3276608479209
853 aime26_28 10 107 [1, '1'] True False 147 16384 282.0846736780368
854 aime26_27 22 223 [250, '250'] True False 166 16384 346.0215881970944
855 aime26_27 0 223 [18, '18'] True False 166 16384 393.94126045296434
856 aime26_27 9 223 ['53.2 + (42'] True False 166 16384 378.9539484800771
857 aime26_27 28 223 [3, '3'] True False 166 16384 349.6967982639326
858 aime26_27 16 223 [1, '1'] True False 166 16384 365.5754593710881
859 aime26_27 8 223 ['(-50000 / 324) * (18'] True False 166 16384 381.89706672297325
860 aime26_27 19 223 [151/2, '151/2'] True False 166 16384 365.2360630449839
861 aime26_28 12 107 [2, '2'] True False 147 16384 304.1952334990492
862 aime26_27 17 223 ['4) *'] True False 166 16384 369.66012714698445
863 aime26_28 7 107 [1, '1'] True False 147 16384 323.19515450601466
864 aime26_27 12 223 [3, '3'] True False 166 16384 383.288970669033
865 aime26_28 29 107 [2, '2'] True False 147 16384 262.5571686270414
866 aime26_28 2 107 [4040, '4040'] True False 147 16384 348.17122988798656
867 aime26_27 30 223 ['(25*10)/4 +'] True False 166 16384 358.17963873106055
868 aime26_29 26 157 [0, '0'] True False 195 16384 175.19872806896456
869 aime26_27 20 223 ['(250 - 8'] True False 166 16384 381.5267905300716
870 aime26_29 6 157 [0, '0'] True False 195 16384 242.8748624570435
871 aime26_28 18 107 [2, '2'] True False 147 16383 314.10582473804243
872 aime26_28 23 107 [4, '4'] True False 147 16384 308.73773305490613
873 aime26_27 25 223 [3, '3'] True False 166 16379 390.3287081370363
874 aime26_29 7 157 [0, '0'] True False 195 16384 255.01091545901727
875 aime26_26 24 132 [400, '400'] True False 121 16384 465.22309615300037
876 aime26_28 5 107 [4040, '4040'] True False 147 16384 364.6718965120381
877 aime26_28 15 107 [1, '1'] True False 147 16384 344.20414905890357
878 aime26_29 10 157 [1, '1'] True False 195 16384 264.0218444929924
879 aime26_28 30 107 [11, '11'] True False 147 16384 300.4004400020931
880 aime26_29 2 157 [0, '0'] True False 195 16384 284.62930131005123
881 aime26_29 15 157 [0, '0'] True False 195 16384 244.5880734800594
882 aime26_29 3 157 [0, '0'] True False 195 16384 288.2222618589876
883 aime26_28 26 107 [1, '1'] True False 147 16384 329.56962192594074
884 aime26_29 23 157 [12, '12'] True False 195 16384 240.92834797501564
885 aime26_28 4 107 [1, '1'] True False 147 16384 393.4492038799217
886 aime26_28 13 107 [4040, '4040'] True False 147 16384 369.1576433168957
887 aime26_29 12 157 [12, '12'] True False 195 16384 279.49940930493176
888 aime26_28 31 107 [1, '1'] True False 147 16384 326.54274887696374
889 aime26_29 18 157 [0, '0'] True False 195 16384 264.6259099270683
890 aime26_28 14 107 [3, '3'] True False 147 16384 389.1993961900007
891 aime26_28 1 107 [6, '6'] True False 147 16384 429.12123020901345
892 aime26_29 13 157 [5, '5'] True False 195 16384 296.7166396569228
893 aime26_28 3 107 [1, '1'] True False 147 16383 433.07488342910074
894 aime26_30 10 393 [1, '1'] True False 185 16384 218.16461065702606
895 aime26_28 21 107 [2, '2'] True False 147 16384 387.40415473806206
896 aime26_28 11 107 [4040, '4040'] True False 147 16383 414.7845958870603
897 aime26_29 14 157 [6, '6'] True False 195 16384 299.7885254200082
898 aime26_30 2 393 [3, '3'] True False 185 16384 252.9077134410618
899 aime26_29 21 157 [2, '2'] True False 195 16384 288.492613469949
900 aime26_28 9 107 [15, '15'] True False 147 16384 418.55128681694623
901 aime26_29 30 157 [0, '0'] True False 195 16384 267.50345164199825
902 aime26_28 20 107 [4040, '4040'] True False 147 16384 406.1472451380687
903 aime26_29 5 157 [0, '0'] True False 195 16384 349.3457888410194
904 aime26_29 19 157 [0, '0'] True False 195 16384 304.6325058559887
905 aime26_29 1 157 [0, '0'] True False 195 16384 361.89264755300246
906 aime26_28 19 107 [5, '5'] True False 147 16384 413.0106003918918
907 aime26_29 17 157 [0, '0'] True False 195 16384 310.18830033100676
908 aime26_28 22 107 [4040, '4040'] True False 147 16384 408.40169036900625
909 aime26_29 22 157 [0, '0'] True False 195 16384 305.8234552589711
910 aime26_30 15 393 [7, '7'] True False 185 16384 229.84034490399063
911 aime26_30 6 393 [0, '0'] True False 185 16384 261.6910111969337
912 aime26_28 28 107 [1, '1'] True False 147 16384 397.5223415509099
913 aime26_30 18 393 [3, '3'] True False 185 16384 235.98915242298972
914 aime26_29 31 157 [0, '0'] True False 195 16384 288.0310865039937
915 aime26_30 23 393 [3, '3'] True False 185 16384 226.21435520600062
916 aime26_28 16 107 [4040, '4040'] True False 147 16384 437.0885142890038
917 aime26_30 5 393 [3, '3'] True False 185 16384 276.11337151401676
918 aime26_29 20 157 [12, '12'] True False 195 16384 323.71289420092944
919 aime26_30 26 393 [2282, '2282'] True False 185 16384 228.61091381602455
920 aime26_30 31 393 [3, '3'] True False 185 16384 220.9454531579977
921 aime26_29 9 157 [0, '0'] True False 195 16384 365.98939842393156
922 aime26_28 27 107 [4, '4'] True False 147 16384 413.54195650399197
923 aime26_27 24 223 [0, '0'] True False 166 16384 509.60956014401745
924 aime26_30 7 393 [3, '3'] True False 185 16384 274.531192565104
925 aime26_30 14 393 [6 - 1*1, '6-1'] True False 185 16384 252.34907890995964
926 aime26_28 8 107 [4040, '4040'] True False 147 16384 471.27135416003875
927 aime26_29 28 157 [0, '0'] True False 195 16384 310.93023310997523
928 aime26_29 4 157 [1, '1'] True False 195 16384 391.9891784579959
929 aime26_28 0 107 [4, '4'] True False 147 16384 505.383636360988
930 aime26_28 17 107 [1, '1'] True False 147 16383 454.0392167819664
931 aime26_30 3 393 [3, '3'] True False 185 16384 311.4696423159912
932 aime26_29 11 157 [12, '12'] True False 195 16384 376.3988845749991
933 aime26_29 29 157 [0, '0'] True False 195 16384 326.045277684927
934 aime26_29 8 157 [0, '0'] True False 195 16384 396.0882890729699
935 aime26_30 29 393 [1, '1'] True False 185 16384 260.66181260102894
936 aime26_29 24 157 [0, '0'] True False 195 16384 363.2450173749821
937 aime26_30 21 393 [3, '3'] True False 185 16384 276.3218860719353
938 aime26_28 25 107 [1, '1'] True False 147 16384 461.33869856398087
939 aime26_30 30 393 [1, '1'] True False 185 16384 266.3951059760293
940 aime26_30 1 393 [-3, '-3'] True False 185 16384 341.9343742020428
941 aime26_30 20 393 [3, '3'] True False 185 16384 285.0949383949628
942 aime26_30 12 393 [3, '3'] True False 185 16384 310.40236104500946
943 aime26_29 0 157 [-1, '-1'] True False 195 16384 442.3704013460083
944 aime26_30 13 393 [5, '5'] True False 185 16384 315.3205573580926
945 aime26_30 28 393 [3, '3'] True False 185 16384 285.3780611830298
946 aime26_29 27 157 [2, '2'] True False 195 16384 363.95382094103843
947 aime26_30 11 393 [48, '48'] True False 185 16384 324.5613489219686
948 aime26_30 22 393 [27, '27'] True False 185 16384 298.6861351990374
949 aime26_30 4 393 [5, '5'] True False 185 16384 356.6518262309255
950 aime26_29 25 157 [12, '12'] True False 195 16384 392.1982599910116
951 aime26_30 19 393 [2, '2'] True False 185 16384 314.85609510401264
952 aime26_30 0 393 [1, '1'] True False 185 16384 369.5454224089626
953 aime26_30 27 393 [7, '7'] True False 185 16384 309.29820779094007
954 aime26_28 24 107 [1, '1'] True False 147 16384 514.7952828869456
955 aime26_30 16 393 [3, '3'] True False 185 16384 350.6233414460439
956 aime26_30 17 393 [3, '3'] True False 185 16384 369.23099841491785
957 aime26_29 16 157 [4, '4'] True False 195 16384 466.6430242009228
958 aime26_30 9 393 [1, '1'] True False 185 16384 396.09432519890834
959 aime26_30 8 393 [225, '225'] True False 185 16384 407.1750580120133
960 aime26_30 25 393 [9, '9'] True False 185 16384 375.7892609159462
961 aime26_30 24 393 [0, '0'] True False 185 16384 382.94195019907784

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 16384
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 32
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,33 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
aime26_1,1.000,32,32,16383.25
aime26_3,0.031,1,32,16383.91
aime26_2,0.000,0,32,16383.91
aime26_4,0.094,3,32,16384.00
aime26_5,0.594,19,32,16383.97
aime26_6,0.438,14,32,16384.00
aime26_7,0.000,0,32,16384.00
aime26_8,0.156,5,32,16384.00
aime26_9,0.000,0,32,16384.00
aime26_10,0.031,1,32,16383.94
aime26_11,0.000,0,32,16383.91
aime26_12,0.000,0,32,16383.97
aime26_13,0.000,0,32,16383.97
aime26_14,0.000,0,32,16383.94
aime26_15,0.000,0,32,16384.12
aime26_16,0.875,28,32,16384.00
aime26_17,0.000,0,32,16383.97
aime26_18,0.000,0,32,16384.00
aime26_19,0.000,0,32,16384.00
aime26_20,0.344,11,32,16384.88
aime26_21,0.125,4,32,16384.00
aime26_22,0.000,0,32,16384.00
aime26_23,0.000,0,32,16383.88
aime26_24,0.000,0,32,16384.00
aime26_25,0.031,1,32,16383.97
aime26_26,0.000,0,32,16383.97
aime26_27,0.000,0,32,16383.06
aime26_28,0.000,0,32,16383.88
aime26_29,0.000,0,32,16384.00
aime26_30,0.000,0,32,16384.00
Total Accuracy,0.124,119,960,16383.95
1 problem_id accuracy correct_count total_samples avg_output_length
2 aime26_1 1.000 32 32 16383.25
3 aime26_3 0.031 1 32 16383.91
4 aime26_2 0.000 0 32 16383.91
5 aime26_4 0.094 3 32 16384.00
6 aime26_5 0.594 19 32 16383.97
7 aime26_6 0.438 14 32 16384.00
8 aime26_7 0.000 0 32 16384.00
9 aime26_8 0.156 5 32 16384.00
10 aime26_9 0.000 0 32 16384.00
11 aime26_10 0.031 1 32 16383.94
12 aime26_11 0.000 0 32 16383.91
13 aime26_12 0.000 0 32 16383.97
14 aime26_13 0.000 0 32 16383.97
15 aime26_14 0.000 0 32 16383.94
16 aime26_15 0.000 0 32 16384.12
17 aime26_16 0.875 28 32 16384.00
18 aime26_17 0.000 0 32 16383.97
19 aime26_18 0.000 0 32 16384.00
20 aime26_19 0.000 0 32 16384.00
21 aime26_20 0.344 11 32 16384.88
22 aime26_21 0.125 4 32 16384.00
23 aime26_22 0.000 0 32 16384.00
24 aime26_23 0.000 0 32 16383.88
25 aime26_24 0.000 0 32 16384.00
26 aime26_25 0.031 1 32 16383.97
27 aime26_26 0.000 0 32 16383.97
28 aime26_27 0.000 0 32 16383.06
29 aime26_28 0.000 0 32 16383.88
30 aime26_29 0.000 0 32 16384.00
31 aime26_30 0.000 0 32 16384.00
32 Total Accuracy 0.124 119 960 16383.95

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,10228554,65.0313949584961
2,1580873,10.050919850667318
3,729034,4.635073343912761
4,3190179,20.282611846923828
Total Tokens,15728640,100.0
1 iter_count token_count percentage
2 1 10228554 65.0313949584961
3 2 1580873 10.050919850667318
4 3 729034 4.635073343912761
5 4 3190179 20.282611846923828
6 Total Tokens 15728640 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@32": 0.3667,
"cons@32": 0.2,
"avg@32": 0.124,
"avg_output_length": 16383.95,
"num_problems": 30,
"num_samples": 960,
"repeat_size": 32,
"avg_request_time": 322.613,
"end_2_end_time": 2621.2656,
"token_throughtput": 6000.3805,
"request_throught": 0.3662,
"avg_iter_count": 1.8017,
"total_concurrency": 128,
"failed_requests": 0
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc814b682fc605f679908d3041cb0e321d442de527e00d1ee3c9cf73e7eebbe7
size 49536771

View File

@@ -0,0 +1,321 @@
problem_id,sample_idx,correct_answer,predicted_answer,has_answer,is_correct,input_tokens,output_tokens,processing_time
amc23_0,2,27,"[27, '27']",True,True,95,8192,61.19195008894894
amc23_0,1,27,"[27, '27']",True,True,95,8192,61.27642694103997
amc23_0,5,27,"[27, '27']",True,True,95,8192,61.52825289696921
amc23_11,4,4,"[4, '4']",True,True,145,8192,62.93972586689051
amc23_11,1,4,"[4, '4']",True,True,145,8192,65.65229315997567
amc23_11,2,4,"[4, '4']",True,True,145,8192,66.19745620398317
amc23_11,6,4,"[4, '4']",True,True,145,8192,66.65912842797115
amc23_11,3,4,"[4, '4']",True,True,145,8192,67.03885199408978
amc23_0,4,27,"[27, '27']",True,True,95,8192,67.10823684092611
amc23_0,7,27,"[27, '27']",True,True,95,8192,67.1613379099872
amc23_0,3,27,"[27, '27']",True,True,95,8192,67.31486404908355
amc23_11,5,4,"[4, '4']",True,True,145,8192,67.6391493229894
amc23_2,2,45,"[45, '45']",True,True,43,8192,68.00731831800658
amc23_0,0,27,"[27, '27']",True,True,95,8192,68.10620073706377
amc23_11,7,4,"[4, '4']",True,True,145,8192,68.09940214303788
amc23_1,0,36,"[36, '36']",True,True,55,8192,69.03208137804177
amc23_0,6,27,"[27, '27']",True,True,95,8192,69.29725767008495
amc23_2,1,45,"[45, '45']",True,True,43,8192,71.31620981101878
amc23_12,1,5,"[1, '1']",True,False,144,8192,71.61277995503042
amc23_2,6,45,"[45, '45']",True,True,43,8192,71.83067592000589
amc23_3,1,3159,"[3159, '3159']",True,True,69,8192,72.88087865093257
amc23_2,3,45,"[45, '45']",True,True,43,8192,73.4725944440579
amc23_1,5,36,"[36, '36']",True,True,55,8192,74.43033121095505
amc23_8,6,3,"[1, '1']",True,False,106,8192,75.04780871304683
amc23_2,4,45,"[45, '45']",True,True,43,8192,75.20502092398237
amc23_2,7,45,"[45, '45']",True,True,43,8192,76.42015164799523
amc23_3,2,3159,"[3159, '3159']",True,True,69,8192,77.10048700706102
amc23_3,5,3159,"[3159, '3159']",True,True,69,8192,84.90733016293962
amc23_3,7,3159,"[3159, '3159']",True,True,69,8192,84.97520345100202
amc23_2,5,45,"[45, '45']",True,True,43,8192,85.06538866995834
amc23_11,0,4,"[4, '4']",True,True,145,8192,86.08846736897249
amc23_3,0,3159,"[3159, '3159']",True,True,69,8192,87.4175717679318
amc23_1,7,36,"[36, '36']",True,True,55,8192,89.623260998982
amc23_5,0,7,"[1, '1']",True,False,54,8192,91.63160066097043
amc23_10,3,1,"[20, '20']",True,False,68,8192,92.24776426400058
amc23_2,0,45,"[45, '45']",True,True,43,8192,92.85638868703973
amc23_16,1,5,"[2, '2']",True,False,205,8192,92.89535723300651
amc23_10,7,1,"[1, '1']",True,True,68,8192,94.010804823949
amc23_10,1,1,"[1, '1']",True,True,68,8192,94.45704696304165
amc23_1,1,36,"[36, '36']",True,True,55,8192,96.06367273000069
amc23_10,0,1,"[2023, '2023']",True,False,68,8192,97.5470824710792
amc23_15,3,1,"[6, '6']",True,False,56,8192,98.79429179104045
amc23_17,2,-1,"[3, '3']",True,False,171,8192,99.75268652802333
amc23_8,0,3,['(1/4) * (7/16) + (1/8) * (7/16) + (1/16) * (7/16) + (1/32) * (3/8) + (1/64) * (1/2) + (1/128) * (1/2) + (1/256) * ('],True,False,106,8192,99.80492535396479
amc23_15,6,1,"[0, '0']",True,False,56,8192,100.3857003680896
amc23_10,6,1,"[2023, '2023']",True,False,68,8192,100.70566278195474
amc23_10,5,1,"[2023, '2023']",True,False,68,8192,100.74619731900748
amc23_12,7,5,"[1, '1']",True,False,144,8192,100.85926511802245
amc23_15,0,1,"[1, '1']",True,True,56,8192,101.49640308192465
amc23_17,0,-1,"[0, '0']",True,False,171,8192,101.7563072439516
amc23_5,4,7,"[6, '6']",True,False,54,8192,102.01898606994655
amc23_17,5,-1,"[2, '2']",True,False,171,8192,102.02107857901137
amc23_15,2,1,['3*(4.4)^2*0.05 + 3*(4.4)*(0.05)^2 + (0.'],True,False,56,8192,102.12765050993767
amc23_3,3,3159,"[3159, '3159']",True,True,69,8192,102.18825929996092
amc23_10,4,1,"[1, '1']",True,True,68,8192,102.80096837494057
amc23_7,6,21,"[0, '0']",True,False,88,8192,102.86038984498009
amc23_15,5,1,"[1, '1']",True,True,56,8192,102.9377765780082
amc23_7,1,21,['1/16 + 1/4 + 15/'],True,False,88,8192,103.40771912003402
amc23_1,2,36,"[4, '4']",True,False,55,8192,103.6083783810027
amc23_7,3,21,"[21, '21']",True,True,88,8192,104.23391946300399
amc23_3,6,3159,"[3159, '3159']",True,True,69,8192,104.27369410998654
amc23_17,1,-1,"[-1, '-1']",True,True,171,8191,104.54521225602366
amc23_17,7,-1,"[-5, '-5']",True,False,171,8192,104.9495968609117
amc23_1,6,36,"[36, '36']",True,True,55,8192,105.07099923095666
amc23_17,3,-1,"[3, '3']",True,False,171,8192,105.12564250302967
amc23_7,2,21,['4 - 8 +'],True,False,88,8192,105.2401041429257
amc23_7,5,21,"[0 + 0, '0 + 0']",True,False,88,8192,105.35565404000226
amc23_7,4,21,"[2, '2']",True,False,88,8192,105.43102612893563
amc23_15,1,1,"[8, '8']",True,False,56,8192,105.4537129579112
amc23_4,3,36,"[2/5, '2/5 \n']",True,False,95,8192,106.23286110605113
amc23_14,7,96,"[0 + 0 + 0 + 1, '1 + 0 + 0 + 0']",True,False,76,8192,106.28933678101748
amc23_17,6,-1,"[3, '3']",True,False,171,8192,106.34686361206695
amc23_4,6,36,"[1.40000000000000, '1.4']",True,False,95,8192,106.73986428405624
amc23_7,7,21,"[1, '1']",True,False,88,8192,107.06941087800078
amc23_8,1,3,['(2^8 - 1)/'],True,False,106,8192,107.0993839049479
amc23_1,3,36,"[3, '3']",True,False,55,8192,107.24456221295986
amc23_3,4,3159,"[3159, '3159']",True,True,69,8192,107.35431011789478
amc23_10,2,1,"[17, '17']",True,False,68,8192,107.5450904170284
amc23_4,1,36,"[2, '2']",True,False,95,8192,107.59094943106174
amc23_15,4,1,"[72, '72']",True,False,56,8192,107.77107457490638
amc23_12,3,5,"[6, '6']",True,False,144,8192,107.84035392804071
amc23_15,7,1,"[5425, '5425']",True,False,56,8192,107.97695979906712
amc23_5,3,7,"[7, '7']",True,True,54,8192,108.30076171294786
amc23_14,5,96,"[-3, '-3']",True,False,76,8192,109.06786018400453
amc23_14,0,96,"[-1, '-1']",True,False,76,8192,109.99035765405279
amc23_14,4,96,"[1, '1']",True,False,76,8192,110.21365635306574
amc23_12,5,5,"[2, '2']",True,False,144,8192,110.3157766830409
amc23_8,5,3,"[1/2, '1/2']",True,False,106,8192,110.60652238794137
amc23_14,2,96,"[1, '1']",True,False,76,8192,111.34138802299276
amc23_5,6,7,"[7, '7']",True,True,54,8192,111.76905206695665
amc23_14,6,96,"[1, '1']",True,False,76,8192,111.98581581597682
amc23_16,6,5,"[10, '10']",True,False,205,8192,112.06418085994665
amc23_4,5,36,"[36, '36']",True,True,95,8192,112.52547956199851
amc23_4,4,36,"[5.25000000000000, '5.25']",True,False,95,8189,112.93002303503454
amc23_1,4,36,"[9, '9']",True,False,55,8192,113.13609343697317
amc23_4,7,36,['1)/2. \n'],True,False,95,8192,113.4193370230496
amc23_17,4,-1,"[2, '2']",True,False,171,8188,113.68232220702339
amc23_4,0,36,"[2, '2']",True,False,95,8192,113.89037251402624
amc23_8,7,3,"[1*1/(4*3), '1/4 * (1/3)']",True,False,106,8192,114.1582665820606
amc23_16,7,5,"[2, '2']",True,False,205,8192,114.14849420601968
amc23_5,5,7,"[7, '7']",True,True,54,8192,114.24884326593019
amc23_5,2,7,"[7, '7']",True,True,54,8192,114.5753069469938
amc23_14,1,96,"[2**1*3, '2^1 * 3']",True,False,76,8192,114.82930766302161
amc23_4,2,36,"[6, '6']",True,False,95,8192,115.06119744502939
amc23_8,4,3,"[1, '1']",True,False,106,8192,115.17143281805329
amc23_13,3,29,"[2, '2']",True,False,231,8192,115.52866659697611
amc23_14,3,96,"[3, '3']",True,False,76,8192,115.91214998508804
amc23_5,7,7,"[2, '2']",True,False,54,8192,116.09522147104144
amc23_7,0,21,"[1, '1']",True,False,88,8192,116.2426409519976
amc23_8,2,3,"[1, '1']",True,False,106,8192,117.99496428098064
amc23_12,2,5,"[1, '1']",True,False,144,8192,118.16161304700654
amc23_5,1,7,"[7, '7']",True,True,54,8192,118.29767964209896
amc23_12,0,5,"[5, '5']",True,True,144,8192,120.31705285399221
amc23_12,4,5,"[1, '1']",True,False,144,8192,120.3673126270296
amc23_12,6,5,"[1, '1']",True,False,144,8192,122.40456652909052
amc23_8,3,3,"[1, '1']",True,False,106,8192,122.52453305595554
amc23_16,4,5,"[3, '3']",True,False,205,8192,123.12153989600483
amc23_13,7,29,"[2, '2']",True,False,231,8192,124.16415566706564
amc23_16,5,5,"[3, '3']",True,False,205,8192,125.5122728390852
amc23_13,4,29,"[0.0145000000000000, '0.0145']",True,False,231,8192,125.97233668901026
amc23_16,2,5,"[0, '0']",True,False,205,8192,126.33154707995709
amc23_13,1,29,"[3, '3']",True,False,231,8192,127.10273033101112
amc23_16,3,5,"[4, '4']",True,False,205,8192,128.24814225896262
amc23_13,5,29,"[2, '2']",True,False,231,8192,128.4197636799654
amc23_13,0,29,"[2, '2']",True,False,231,8192,128.8427458270453
amc23_16,0,5,"[1, '1']",True,False,205,8192,128.966336366022
amc23_13,6,29,"[2, '2']",True,False,231,8192,129.52601856202818
amc23_13,2,29,"[1320, '1320']",True,False,231,8192,133.4044885430485
amc23_19,7,18,"[18, '18']",True,True,49,8192,90.64665627398062
amc23_18,1,8,"[8, '8']",True,True,37,8192,100.9174827550305
amc23_18,2,8,"[8, '8']",True,True,37,8192,101.1499934270978
amc23_21,1,9,"[9, '9']",True,True,114,8192,87.72177464398555
amc23_18,7,8,"[8, '8']",True,True,37,8192,97.14539123291615
amc23_22,2,9,"[0.100000000000000, '0.1']",True,False,116,8192,72.22311288502533
amc23_21,0,9,"[9, '9']",True,True,114,8192,90.68150967103429
amc23_18,6,8,"[8, '8']",True,True,37,8192,100.00468590902165
amc23_23,2,7,"[7, '7']",True,True,88,8192,68.22982985898852
amc23_19,1,18,"[0, '0']",True,False,49,8192,100.95411699498072
amc23_19,6,18,"[18, '18']",True,True,49,8192,101.85972683597356
amc23_19,2,18,"[18, '18']",True,True,49,8192,103.99151428299956
amc23_23,6,7,"[7, '7']",True,True,88,8192,71.28314636601135
amc23_23,3,7,"[7, '7']",True,True,88,8192,74.42636467597913
amc23_21,2,9,"[9, '9']",True,True,114,8192,97.17080385494046
amc23_18,5,8,"[8, '8']",True,True,37,8192,108.47706348495558
amc23_19,3,18,"[18, '18']",True,True,49,8192,107.15747047297191
amc23_22,7,9,"[28, '28']",True,False,116,8192,79.23446922597941
amc23_23,0,7,"[7, '7']",True,True,88,8192,78.13250622700434
amc23_23,7,7,"[7, '7']",True,True,88,8192,75.37223018601071
amc23_18,3,8,"[8, '8']",True,True,37,8192,115.27758420305327
amc23_22,6,9,"[1, '1']",True,False,116,8192,85.06932995899115
amc23_21,7,9,"[9, '9']",True,True,114,8192,92.13574443594553
amc23_23,4,7,"[7, '7']",True,True,88,8192,79.18420834594872
amc23_18,0,8,"[8, '8']",True,True,37,8192,120.16090293799061
amc23_19,0,18,"[18, '18']",True,True,49,8192,114.89158774795942
amc23_21,5,9,"[9, '9']",True,True,114,8192,97.94533954397775
amc23_21,4,9,"[9, '9']",True,True,114,8192,98.28490048600361
amc23_19,5,18,"[18, '18']",True,True,49,8192,117.34300446195994
amc23_26,6,7,"[7, '7']",True,True,143,8192,80.8017051880015
amc23_28,4,50,"[50, '50']",True,True,97,8192,78.73091553302947
amc23_28,2,50,"[50, '50']",True,True,97,8192,79.83393824496306
amc23_28,5,50,"[50, '50']",True,True,97,8192,79.6148916319944
amc23_29,0,13,"[{9/4, 13}, '\\frac{9}{4},13']",True,False,149,8192,79.98158943594899
amc23_18,4,8,"[8, '8']",True,True,37,8192,122.31027306395117
amc23_21,3,9,"[9, '9']",True,True,114,8192,103.2096158680506
amc23_29,2,13,"[13, '13']",True,True,149,8192,79.97314536198974
amc23_26,7,7,"[7, '7']",True,True,143,8192,87.4679494210286
amc23_27,1,13,"[13, '13']",True,True,91,8192,87.48455858405214
amc23_29,5,13,"[{9/4, 13}, '\\frac{9}{4},13']",True,False,149,8192,82.51265329297166
amc23_28,0,50,"[50, '50']",True,True,97,8192,86.86943171394523
amc23_25,6,7,"[7, '7']",True,True,132,8192,92.07869001710787
amc23_26,1,7,"[7, '7']",True,True,143,8192,92.08995558100287
amc23_28,1,50,"[50, '50']",True,True,97,8192,88.60455629893113
amc23_28,7,50,"[50, '50']",True,True,97,8192,90.80266497703269
amc23_26,3,7,"[{2/5, 7}, '\\frac{2}{5},7']",True,False,143,8192,95.41276095097419
amc23_36,4,50,"[50, '50']",True,True,101,8192,78.4291304621147
amc23_33,1,18,"[18, '18']",True,True,101,8192,86.09201944805682
amc23_29,3,13,"[13, '13']",True,True,149,8192,92.64970691001508
amc23_28,3,50,"[50, '50']",True,True,97,8192,94.72743196296506
amc23_22,3,9,"[0, '0']",True,False,116,8192,109.38795106997713
amc23_23,1,7,"[7, '7']",True,True,88,8192,103.60559388296679
amc23_32,1,11,"[28, '28']",True,False,80,8192,89.03565453109331
amc23_20,3,265,"[1, '1']",True,False,100,8192,131.58029193198308
amc23_19,4,18,"[32768*7, '32768 * 7']",True,False,49,8192,136.43456535506994
amc23_36,0,50,"[50, '50']",True,True,101,8192,84.73916723008733
amc23_26,0,7,"[7, '7']",True,True,143,8192,102.66835822106805
amc23_25,5,7,"[7, '7']",True,True,132,8192,103.68845860206056
amc23_26,5,7,"[7, '7']",True,True,143,8192,101.64373672800139
amc23_21,6,9,"[9, '9']",True,True,114,8192,120.29043235001154
amc23_29,1,13,"[13, '13']",True,True,149,8192,99.07692185998894
amc23_20,1,265,['(1/6) *'],True,False,100,8192,136.53075886599254
amc23_32,4,11,['7. 29 - 15'],True,False,80,8192,94.25040446699131
amc23_27,4,13,"[13, '13']",True,True,91,8192,103.2735300869681
amc23_20,6,265,"[1 - (5/6)**4.0, '1 - (5/6)^4.']",True,False,100,8192,135.0768851779867
amc23_26,4,7,"[2/5.0, '2/5.']",True,False,143,8192,105.23981978790835
amc23_32,7,11,"[1, '1']",True,False,80,8192,94.97119355702307
amc23_27,2,13,"[13, '13']",True,True,91,8192,105.0305475180503
amc23_27,0,13,"[13, '13']",True,True,91,8192,105.7328872049693
amc23_29,7,13,"[13, '13']",True,True,149,8192,100.92962065397296
amc23_27,5,13,"[13, '13']",True,True,91,8192,106.06754230498336
amc23_29,6,13,"[13, '13']",True,True,149,8192,102.37299207702745
amc23_32,6,11,"[5, '5']",True,False,80,8192,98.14940637897234
amc23_22,0,9,"[3, '3']",True,False,116,8192,123.80365203099791
amc23_23,5,7,"[7, '7']",True,True,88,8192,113.4984670530539
amc23_27,7,13,"[0.600000000000000, '0.6']",True,False,91,8192,108.83173933892976
amc23_33,0,18,"[18, '18']",True,True,101,8192,101.35195924597792
amc23_27,3,13,"[13, '13']",True,True,91,8192,111.37359171302523
amc23_26,2,7,"[7, '7']",True,True,143,8192,113.27874053199776
amc23_20,5,265,"[1296, '1296']",True,False,100,8192,143.99710955901537
amc23_32,3,11,"[1, '1']",True,False,80,8192,103.34868318098597
amc23_36,5,50,"[50, '50']",True,True,101,8192,93.4008934290614
amc23_25,1,7,"[1/3.0, '1/3.']",True,False,132,8192,116.14001861901488
amc23_33,6,18,"[12.909*6.9, '12.909 * 6.9']",True,False,101,8192,100.17435073200613
amc23_36,7,50,"[50, '50']",True,True,101,8192,93.00405342900194
amc23_33,5,18,"[18, '18']",True,True,101,8192,101.58143021399155
amc23_32,5,11,"[101, '101']",True,False,80,8193,105.08686058607418
amc23_29,4,13,"[13, '13']",True,True,149,8192,110.06985095702112
amc23_22,1,9,"[372, '372']",True,False,116,8192,128.46842872491106
amc23_32,2,11,"[14, '14']",True,False,80,8192,106.06993949599564
amc23_33,3,18,"[18, '18']",True,True,101,8192,104.67234957893379
amc23_20,0,265,"[0, '0']",True,False,100,8192,151.59554938203655
amc23_20,2,265,"[3, '3']",True,False,100,8192,149.26186313095968
amc23_36,2,50,"[50, '50']",True,True,101,8192,98.95953804405872
amc23_25,4,7,"[1/6.0, '1/6.\n']",True,False,132,8192,119.63788494304754
amc23_33,2,18,"[6, '6']",True,False,101,8192,106.19234514702111
amc23_25,3,7,"[1/2.0, '1/2.']",True,False,132,8192,121.71394772001076
amc23_30,6,5,"[3, '3']",True,False,52,8192,110.72991988004651
amc23_25,7,7,"[35, '35']",True,False,132,8192,122.51419615000486
amc23_25,0,7,"[7, '7']",True,True,132,8192,126.11816675704904
amc23_20,7,265,"[15, '15']",True,False,100,8192,155.29975685302634
amc23_30,2,5,"[2, '2']",True,False,52,8192,118.50598007801455
amc23_22,4,9,"[2, '2']",True,False,116,8192,137.73798931809142
amc23_30,7,5,"[4, '4']",True,False,52,8192,117.6527527780272
amc23_30,1,5,['-1)\n'],True,False,52,8191,120.94747834291775
amc23_33,4,18,"[18, '18']",True,True,101,8192,116.82629583601374
amc23_33,7,18,"[18, '18']",True,True,101,8192,114.88910927006509
amc23_28,6,50,"[440, '440']",True,False,97,8192,125.95157545409165
amc23_36,6,50,"[50, '50']",True,True,101,8192,108.96922374202404
amc23_25,2,7,"[7, '7']",True,True,132,8192,132.62190893501975
amc23_32,0,11,['1*10 + 2*6 +'],True,False,80,8193,123.44200975005515
amc23_30,3,5,"[-3, '-3']",True,False,52,8192,125.32482891203836
amc23_22,5,9,"[0, '0']",True,False,116,8192,147.18258160201367
amc23_27,6,13,"[13, '13']",True,True,91,8192,135.2919422989944
amc23_20,4,265,"[3, '3']",True,False,100,8192,169.53860774997156
amc23_36,1,50,"[50, '50']",True,True,101,8192,124.80863759992644
amc23_36,3,50,"[50, '50']",True,True,101,8192,123.346381515963
amc23_30,0,5,"[24, '24']",True,False,52,8190,134.52100193710066
amc23_30,5,5,"[2, '2']",True,False,52,8192,134.5675000550691
amc23_43,3,194,"[194, '194']",True,True,113,8192,76.50545846298337
amc23_44,0,1625,"[1625, '1625']",True,True,65,8192,73.72094948706217
amc23_44,7,1625,"[1625, '1625']",True,True,65,8192,68.99611517100129
amc23_43,5,194,"[194, '194']",True,True,113,8192,75.64769548899494
amc23_43,1,194,"[194, '194']",True,True,113,8192,81.87070783996023
amc23_44,2,1625,"[1625, '1625']",True,True,65,8192,74.75722070003394
amc23_30,4,5,"[4, '4']",True,False,52,8192,138.57616749301087
amc23_43,2,194,"[194, '194']",True,True,113,8192,81.25590009696316
amc23_44,4,1625,"[1625, '1625']",True,True,65,8192,74.51399209094234
amc23_43,7,194,"[194, '194']",True,True,113,8192,79.12258289707825
amc23_40,0,11,"[12, '12']",True,False,52,8192,127.7509328359738
amc23_40,5,11,"[0, '0']",True,False,52,8192,125.41851273609791
amc23_44,1,1625,"[1625, '1625']",True,True,65,8192,79.91086279402953
amc23_44,5,1625,"[1625, '1625']",True,True,65,8192,76.03660052805208
amc23_43,6,194,"[194, '194']",True,True,113,8192,82.76726872497238
amc23_44,3,1625,"[1625, '1625']",True,True,65,8192,80.81791399000213
amc23_43,4,194,"[194, '194']",True,True,113,8192,89.84170640306547
amc23_44,6,1625,"[1625, '1625']",True,True,65,8192,84.02751414501108
amc23_40,2,11,"[6, '6']",True,False,52,8192,136.47187170991674
amc23_40,7,11,"[1, '1']",True,False,52,8192,133.55518094298895
amc23_45,2,4,"[3, '3']",True,False,134,8192,85.19560115900822
amc23_41,1,3,"[4, '4']",True,False,232,8192,106.12409789999947
amc23_41,0,3,"[2, '2']",True,False,232,8192,109.99717283295467
amc23_47,6,901,"[0, '0']",True,False,72,8192,68.09748758305795
amc23_40,4,11,"[5, '5']",True,False,52,8192,146.58534501399845
amc23_43,0,194,"[194, '194']",True,True,113,8192,108.1631193900248
amc23_40,6,11,"[3, '3']",True,False,52,8192,146.67214590497315
amc23_41,2,3,"[2, '2']",True,False,232,8192,114.6246078920085
amc23_41,7,3,"[2, '2']",True,False,232,8192,113.28283428493887
amc23_40,1,11,['0)\n'],True,False,52,8192,153.70327479508705
amc23_41,3,3,"[3, '3']",True,True,232,8192,117.59636711794883
amc23_41,5,3,"[4, '4']",True,False,232,8192,121.3757939360803
amc23_41,6,3,"[0, '0']",True,False,232,8192,120.55719395296182
amc23_41,4,3,"[3, '3']",True,True,232,8192,127.00377039599698
amc23_40,3,11,"[1, '1']",True,False,52,8192,165.2669527590042
amc23_45,1,4,"[8, '8']",True,False,134,8192,111.99631542200223
amc23_47,2,901,"[999, '999']",True,False,72,8192,100.02184757392388
amc23_49,5,8,"[2, '2']",True,False,55,8192,89.85825391602702
amc23_46,1,6,"[0, '0']",True,False,99,8192,112.94967331597582
amc23_47,3,901,"[999, '999']",True,False,72,8192,105.72023175493814
amc23_48,0,144,"[3, '3']",True,False,92,8192,100.4109142839443
amc23_48,6,144,"[144, '144']",True,True,92,8192,99.23151853494346
amc23_47,0,901,"[900, '900']",True,False,72,8192,110.1760751530528
amc23_45,5,4,"[3, '3']",True,False,134,8192,118.01113523892127
amc23_46,2,6,"[2, '2']",True,False,99,8192,116.38127740600612
amc23_45,6,4,"[6, '6']",True,False,134,8192,119.06724345101975
amc23_48,2,144,['1). \n'],True,False,92,8192,103.23088083101902
amc23_46,3,6,"[1, '1']",True,False,99,8192,117.56262404005975
amc23_48,5,144,"[1, '1']",True,False,92,8192,104.18325246800669
amc23_48,4,144,"[144, '144']",True,True,92,8192,106.01285172509961
amc23_45,7,4,"[2, '2']",True,False,134,8192,122.03002966206986
amc23_47,7,901,['3).'],True,False,72,8192,107.72763259895146
amc23_49,1,8,"[1, '1']",True,False,55,8192,104.14076177403331
amc23_46,0,6,['2)\n3. (2'],True,False,99,8192,123.11878581799101
amc23_49,2,8,"[2, '2']",True,False,55,8192,104.14129159902222
amc23_49,4,8,"[0, '0']",True,False,55,8192,104.36290648498107
amc23_47,1,901,"[100, '100']",True,False,72,8192,116.60050178796519
amc23_46,7,6,"[5, '5']",True,False,99,8191,119.27038910891861
amc23_47,5,901,"[999, '999']",True,False,72,8192,112.39885503100231
amc23_48,1,144,['1 ).'],True,False,92,8192,110.12675413594116
amc23_45,3,4,"[2, '2']",True,False,134,8192,129.43085643602535
amc23_46,4,6,"[3, '3']",True,False,99,8192,124.42130887892563
amc23_47,4,901,"[901, '901']",True,True,72,8192,114.14520193496719
amc23_48,7,144,"[233, '233']",True,False,92,8192,108.05754708801396
amc23_49,0,8,['0.5)\n\n-'],True,False,55,8192,107.90004588407464
amc23_46,6,6,"[11, '11']",True,False,99,8192,121.42186184797902
amc23_46,5,6,"[10, '10']",True,False,99,8192,121.73959818901494
amc23_45,0,4,"[3, '3']",True,False,134,8192,133.02634463005234
amc23_49,6,8,"[0, '0']",True,False,55,8192,106.13942024903372
amc23_49,3,8,['1).'],True,False,55,8192,109.3490971380379
amc23_49,7,8,"[0, '0']",True,False,55,8192,107.16895192000084
amc23_45,4,4,"[1, '1']",True,False,134,8192,133.75850401399657
amc23_48,3,144,"[0, '0']",True,False,92,8192,118.62594668800011
1 problem_id sample_idx correct_answer predicted_answer has_answer is_correct input_tokens output_tokens processing_time
2 amc23_0 2 27 [27, '27'] True True 95 8192 61.19195008894894
3 amc23_0 1 27 [27, '27'] True True 95 8192 61.27642694103997
4 amc23_0 5 27 [27, '27'] True True 95 8192 61.52825289696921
5 amc23_11 4 4 [4, '4'] True True 145 8192 62.93972586689051
6 amc23_11 1 4 [4, '4'] True True 145 8192 65.65229315997567
7 amc23_11 2 4 [4, '4'] True True 145 8192 66.19745620398317
8 amc23_11 6 4 [4, '4'] True True 145 8192 66.65912842797115
9 amc23_11 3 4 [4, '4'] True True 145 8192 67.03885199408978
10 amc23_0 4 27 [27, '27'] True True 95 8192 67.10823684092611
11 amc23_0 7 27 [27, '27'] True True 95 8192 67.1613379099872
12 amc23_0 3 27 [27, '27'] True True 95 8192 67.31486404908355
13 amc23_11 5 4 [4, '4'] True True 145 8192 67.6391493229894
14 amc23_2 2 45 [45, '45'] True True 43 8192 68.00731831800658
15 amc23_0 0 27 [27, '27'] True True 95 8192 68.10620073706377
16 amc23_11 7 4 [4, '4'] True True 145 8192 68.09940214303788
17 amc23_1 0 36 [36, '36'] True True 55 8192 69.03208137804177
18 amc23_0 6 27 [27, '27'] True True 95 8192 69.29725767008495
19 amc23_2 1 45 [45, '45'] True True 43 8192 71.31620981101878
20 amc23_12 1 5 [1, '1'] True False 144 8192 71.61277995503042
21 amc23_2 6 45 [45, '45'] True True 43 8192 71.83067592000589
22 amc23_3 1 3159 [3159, '3159'] True True 69 8192 72.88087865093257
23 amc23_2 3 45 [45, '45'] True True 43 8192 73.4725944440579
24 amc23_1 5 36 [36, '36'] True True 55 8192 74.43033121095505
25 amc23_8 6 3 [1, '1'] True False 106 8192 75.04780871304683
26 amc23_2 4 45 [45, '45'] True True 43 8192 75.20502092398237
27 amc23_2 7 45 [45, '45'] True True 43 8192 76.42015164799523
28 amc23_3 2 3159 [3159, '3159'] True True 69 8192 77.10048700706102
29 amc23_3 5 3159 [3159, '3159'] True True 69 8192 84.90733016293962
30 amc23_3 7 3159 [3159, '3159'] True True 69 8192 84.97520345100202
31 amc23_2 5 45 [45, '45'] True True 43 8192 85.06538866995834
32 amc23_11 0 4 [4, '4'] True True 145 8192 86.08846736897249
33 amc23_3 0 3159 [3159, '3159'] True True 69 8192 87.4175717679318
34 amc23_1 7 36 [36, '36'] True True 55 8192 89.623260998982
35 amc23_5 0 7 [1, '1'] True False 54 8192 91.63160066097043
36 amc23_10 3 1 [20, '20'] True False 68 8192 92.24776426400058
37 amc23_2 0 45 [45, '45'] True True 43 8192 92.85638868703973
38 amc23_16 1 5 [2, '2'] True False 205 8192 92.89535723300651
39 amc23_10 7 1 [1, '1'] True True 68 8192 94.010804823949
40 amc23_10 1 1 [1, '1'] True True 68 8192 94.45704696304165
41 amc23_1 1 36 [36, '36'] True True 55 8192 96.06367273000069
42 amc23_10 0 1 [2023, '2023'] True False 68 8192 97.5470824710792
43 amc23_15 3 1 [6, '6'] True False 56 8192 98.79429179104045
44 amc23_17 2 -1 [3, '3'] True False 171 8192 99.75268652802333
45 amc23_8 0 3 ['(1/4) * (7/16) + (1/8) * (7/16) + (1/16) * (7/16) + (1/32) * (3/8) + (1/64) * (1/2) + (1/128) * (1/2) + (1/256) * ('] True False 106 8192 99.80492535396479
46 amc23_15 6 1 [0, '0'] True False 56 8192 100.3857003680896
47 amc23_10 6 1 [2023, '2023'] True False 68 8192 100.70566278195474
48 amc23_10 5 1 [2023, '2023'] True False 68 8192 100.74619731900748
49 amc23_12 7 5 [1, '1'] True False 144 8192 100.85926511802245
50 amc23_15 0 1 [1, '1'] True True 56 8192 101.49640308192465
51 amc23_17 0 -1 [0, '0'] True False 171 8192 101.7563072439516
52 amc23_5 4 7 [6, '6'] True False 54 8192 102.01898606994655
53 amc23_17 5 -1 [2, '2'] True False 171 8192 102.02107857901137
54 amc23_15 2 1 ['3*(4.4)^2*0.05 + 3*(4.4)*(0.05)^2 + (0.'] True False 56 8192 102.12765050993767
55 amc23_3 3 3159 [3159, '3159'] True True 69 8192 102.18825929996092
56 amc23_10 4 1 [1, '1'] True True 68 8192 102.80096837494057
57 amc23_7 6 21 [0, '0'] True False 88 8192 102.86038984498009
58 amc23_15 5 1 [1, '1'] True True 56 8192 102.9377765780082
59 amc23_7 1 21 ['1/16 + 1/4 + 15/'] True False 88 8192 103.40771912003402
60 amc23_1 2 36 [4, '4'] True False 55 8192 103.6083783810027
61 amc23_7 3 21 [21, '21'] True True 88 8192 104.23391946300399
62 amc23_3 6 3159 [3159, '3159'] True True 69 8192 104.27369410998654
63 amc23_17 1 -1 [-1, '-1'] True True 171 8191 104.54521225602366
64 amc23_17 7 -1 [-5, '-5'] True False 171 8192 104.9495968609117
65 amc23_1 6 36 [36, '36'] True True 55 8192 105.07099923095666
66 amc23_17 3 -1 [3, '3'] True False 171 8192 105.12564250302967
67 amc23_7 2 21 ['4 - 8 +'] True False 88 8192 105.2401041429257
68 amc23_7 5 21 [0 + 0, '0 + 0'] True False 88 8192 105.35565404000226
69 amc23_7 4 21 [2, '2'] True False 88 8192 105.43102612893563
70 amc23_15 1 1 [8, '8'] True False 56 8192 105.4537129579112
71 amc23_4 3 36 [2/5, '2/5 \n'] True False 95 8192 106.23286110605113
72 amc23_14 7 96 [0 + 0 + 0 + 1, '1 + 0 + 0 + 0'] True False 76 8192 106.28933678101748
73 amc23_17 6 -1 [3, '3'] True False 171 8192 106.34686361206695
74 amc23_4 6 36 [1.40000000000000, '1.4'] True False 95 8192 106.73986428405624
75 amc23_7 7 21 [1, '1'] True False 88 8192 107.06941087800078
76 amc23_8 1 3 ['(2^8 - 1)/'] True False 106 8192 107.0993839049479
77 amc23_1 3 36 [3, '3'] True False 55 8192 107.24456221295986
78 amc23_3 4 3159 [3159, '3159'] True True 69 8192 107.35431011789478
79 amc23_10 2 1 [17, '17'] True False 68 8192 107.5450904170284
80 amc23_4 1 36 [2, '2'] True False 95 8192 107.59094943106174
81 amc23_15 4 1 [72, '72'] True False 56 8192 107.77107457490638
82 amc23_12 3 5 [6, '6'] True False 144 8192 107.84035392804071
83 amc23_15 7 1 [5425, '5425'] True False 56 8192 107.97695979906712
84 amc23_5 3 7 [7, '7'] True True 54 8192 108.30076171294786
85 amc23_14 5 96 [-3, '-3'] True False 76 8192 109.06786018400453
86 amc23_14 0 96 [-1, '-1'] True False 76 8192 109.99035765405279
87 amc23_14 4 96 [1, '1'] True False 76 8192 110.21365635306574
88 amc23_12 5 5 [2, '2'] True False 144 8192 110.3157766830409
89 amc23_8 5 3 [1/2, '1/2'] True False 106 8192 110.60652238794137
90 amc23_14 2 96 [1, '1'] True False 76 8192 111.34138802299276
91 amc23_5 6 7 [7, '7'] True True 54 8192 111.76905206695665
92 amc23_14 6 96 [1, '1'] True False 76 8192 111.98581581597682
93 amc23_16 6 5 [10, '10'] True False 205 8192 112.06418085994665
94 amc23_4 5 36 [36, '36'] True True 95 8192 112.52547956199851
95 amc23_4 4 36 [5.25000000000000, '5.25'] True False 95 8189 112.93002303503454
96 amc23_1 4 36 [9, '9'] True False 55 8192 113.13609343697317
97 amc23_4 7 36 ['1)/2. \n'] True False 95 8192 113.4193370230496
98 amc23_17 4 -1 [2, '2'] True False 171 8188 113.68232220702339
99 amc23_4 0 36 [2, '2'] True False 95 8192 113.89037251402624
100 amc23_8 7 3 [1*1/(4*3), '1/4 * (1/3)'] True False 106 8192 114.1582665820606
101 amc23_16 7 5 [2, '2'] True False 205 8192 114.14849420601968
102 amc23_5 5 7 [7, '7'] True True 54 8192 114.24884326593019
103 amc23_5 2 7 [7, '7'] True True 54 8192 114.5753069469938
104 amc23_14 1 96 [2**1*3, '2^1 * 3'] True False 76 8192 114.82930766302161
105 amc23_4 2 36 [6, '6'] True False 95 8192 115.06119744502939
106 amc23_8 4 3 [1, '1'] True False 106 8192 115.17143281805329
107 amc23_13 3 29 [2, '2'] True False 231 8192 115.52866659697611
108 amc23_14 3 96 [3, '3'] True False 76 8192 115.91214998508804
109 amc23_5 7 7 [2, '2'] True False 54 8192 116.09522147104144
110 amc23_7 0 21 [1, '1'] True False 88 8192 116.2426409519976
111 amc23_8 2 3 [1, '1'] True False 106 8192 117.99496428098064
112 amc23_12 2 5 [1, '1'] True False 144 8192 118.16161304700654
113 amc23_5 1 7 [7, '7'] True True 54 8192 118.29767964209896
114 amc23_12 0 5 [5, '5'] True True 144 8192 120.31705285399221
115 amc23_12 4 5 [1, '1'] True False 144 8192 120.3673126270296
116 amc23_12 6 5 [1, '1'] True False 144 8192 122.40456652909052
117 amc23_8 3 3 [1, '1'] True False 106 8192 122.52453305595554
118 amc23_16 4 5 [3, '3'] True False 205 8192 123.12153989600483
119 amc23_13 7 29 [2, '2'] True False 231 8192 124.16415566706564
120 amc23_16 5 5 [3, '3'] True False 205 8192 125.5122728390852
121 amc23_13 4 29 [0.0145000000000000, '0.0145'] True False 231 8192 125.97233668901026
122 amc23_16 2 5 [0, '0'] True False 205 8192 126.33154707995709
123 amc23_13 1 29 [3, '3'] True False 231 8192 127.10273033101112
124 amc23_16 3 5 [4, '4'] True False 205 8192 128.24814225896262
125 amc23_13 5 29 [2, '2'] True False 231 8192 128.4197636799654
126 amc23_13 0 29 [2, '2'] True False 231 8192 128.8427458270453
127 amc23_16 0 5 [1, '1'] True False 205 8192 128.966336366022
128 amc23_13 6 29 [2, '2'] True False 231 8192 129.52601856202818
129 amc23_13 2 29 [1320, '1320'] True False 231 8192 133.4044885430485
130 amc23_19 7 18 [18, '18'] True True 49 8192 90.64665627398062
131 amc23_18 1 8 [8, '8'] True True 37 8192 100.9174827550305
132 amc23_18 2 8 [8, '8'] True True 37 8192 101.1499934270978
133 amc23_21 1 9 [9, '9'] True True 114 8192 87.72177464398555
134 amc23_18 7 8 [8, '8'] True True 37 8192 97.14539123291615
135 amc23_22 2 9 [0.100000000000000, '0.1'] True False 116 8192 72.22311288502533
136 amc23_21 0 9 [9, '9'] True True 114 8192 90.68150967103429
137 amc23_18 6 8 [8, '8'] True True 37 8192 100.00468590902165
138 amc23_23 2 7 [7, '7'] True True 88 8192 68.22982985898852
139 amc23_19 1 18 [0, '0'] True False 49 8192 100.95411699498072
140 amc23_19 6 18 [18, '18'] True True 49 8192 101.85972683597356
141 amc23_19 2 18 [18, '18'] True True 49 8192 103.99151428299956
142 amc23_23 6 7 [7, '7'] True True 88 8192 71.28314636601135
143 amc23_23 3 7 [7, '7'] True True 88 8192 74.42636467597913
144 amc23_21 2 9 [9, '9'] True True 114 8192 97.17080385494046
145 amc23_18 5 8 [8, '8'] True True 37 8192 108.47706348495558
146 amc23_19 3 18 [18, '18'] True True 49 8192 107.15747047297191
147 amc23_22 7 9 [28, '28'] True False 116 8192 79.23446922597941
148 amc23_23 0 7 [7, '7'] True True 88 8192 78.13250622700434
149 amc23_23 7 7 [7, '7'] True True 88 8192 75.37223018601071
150 amc23_18 3 8 [8, '8'] True True 37 8192 115.27758420305327
151 amc23_22 6 9 [1, '1'] True False 116 8192 85.06932995899115
152 amc23_21 7 9 [9, '9'] True True 114 8192 92.13574443594553
153 amc23_23 4 7 [7, '7'] True True 88 8192 79.18420834594872
154 amc23_18 0 8 [8, '8'] True True 37 8192 120.16090293799061
155 amc23_19 0 18 [18, '18'] True True 49 8192 114.89158774795942
156 amc23_21 5 9 [9, '9'] True True 114 8192 97.94533954397775
157 amc23_21 4 9 [9, '9'] True True 114 8192 98.28490048600361
158 amc23_19 5 18 [18, '18'] True True 49 8192 117.34300446195994
159 amc23_26 6 7 [7, '7'] True True 143 8192 80.8017051880015
160 amc23_28 4 50 [50, '50'] True True 97 8192 78.73091553302947
161 amc23_28 2 50 [50, '50'] True True 97 8192 79.83393824496306
162 amc23_28 5 50 [50, '50'] True True 97 8192 79.6148916319944
163 amc23_29 0 13 [{9/4, 13}, '\\frac{9}{4},13'] True False 149 8192 79.98158943594899
164 amc23_18 4 8 [8, '8'] True True 37 8192 122.31027306395117
165 amc23_21 3 9 [9, '9'] True True 114 8192 103.2096158680506
166 amc23_29 2 13 [13, '13'] True True 149 8192 79.97314536198974
167 amc23_26 7 7 [7, '7'] True True 143 8192 87.4679494210286
168 amc23_27 1 13 [13, '13'] True True 91 8192 87.48455858405214
169 amc23_29 5 13 [{9/4, 13}, '\\frac{9}{4},13'] True False 149 8192 82.51265329297166
170 amc23_28 0 50 [50, '50'] True True 97 8192 86.86943171394523
171 amc23_25 6 7 [7, '7'] True True 132 8192 92.07869001710787
172 amc23_26 1 7 [7, '7'] True True 143 8192 92.08995558100287
173 amc23_28 1 50 [50, '50'] True True 97 8192 88.60455629893113
174 amc23_28 7 50 [50, '50'] True True 97 8192 90.80266497703269
175 amc23_26 3 7 [{2/5, 7}, '\\frac{2}{5},7'] True False 143 8192 95.41276095097419
176 amc23_36 4 50 [50, '50'] True True 101 8192 78.4291304621147
177 amc23_33 1 18 [18, '18'] True True 101 8192 86.09201944805682
178 amc23_29 3 13 [13, '13'] True True 149 8192 92.64970691001508
179 amc23_28 3 50 [50, '50'] True True 97 8192 94.72743196296506
180 amc23_22 3 9 [0, '0'] True False 116 8192 109.38795106997713
181 amc23_23 1 7 [7, '7'] True True 88 8192 103.60559388296679
182 amc23_32 1 11 [28, '28'] True False 80 8192 89.03565453109331
183 amc23_20 3 265 [1, '1'] True False 100 8192 131.58029193198308
184 amc23_19 4 18 [32768*7, '32768 * 7'] True False 49 8192 136.43456535506994
185 amc23_36 0 50 [50, '50'] True True 101 8192 84.73916723008733
186 amc23_26 0 7 [7, '7'] True True 143 8192 102.66835822106805
187 amc23_25 5 7 [7, '7'] True True 132 8192 103.68845860206056
188 amc23_26 5 7 [7, '7'] True True 143 8192 101.64373672800139
189 amc23_21 6 9 [9, '9'] True True 114 8192 120.29043235001154
190 amc23_29 1 13 [13, '13'] True True 149 8192 99.07692185998894
191 amc23_20 1 265 ['(1/6) *'] True False 100 8192 136.53075886599254
192 amc23_32 4 11 ['7. 29 - 15'] True False 80 8192 94.25040446699131
193 amc23_27 4 13 [13, '13'] True True 91 8192 103.2735300869681
194 amc23_20 6 265 [1 - (5/6)**4.0, '1 - (5/6)^4.'] True False 100 8192 135.0768851779867
195 amc23_26 4 7 [2/5.0, '2/5.'] True False 143 8192 105.23981978790835
196 amc23_32 7 11 [1, '1'] True False 80 8192 94.97119355702307
197 amc23_27 2 13 [13, '13'] True True 91 8192 105.0305475180503
198 amc23_27 0 13 [13, '13'] True True 91 8192 105.7328872049693
199 amc23_29 7 13 [13, '13'] True True 149 8192 100.92962065397296
200 amc23_27 5 13 [13, '13'] True True 91 8192 106.06754230498336
201 amc23_29 6 13 [13, '13'] True True 149 8192 102.37299207702745
202 amc23_32 6 11 [5, '5'] True False 80 8192 98.14940637897234
203 amc23_22 0 9 [3, '3'] True False 116 8192 123.80365203099791
204 amc23_23 5 7 [7, '7'] True True 88 8192 113.4984670530539
205 amc23_27 7 13 [0.600000000000000, '0.6'] True False 91 8192 108.83173933892976
206 amc23_33 0 18 [18, '18'] True True 101 8192 101.35195924597792
207 amc23_27 3 13 [13, '13'] True True 91 8192 111.37359171302523
208 amc23_26 2 7 [7, '7'] True True 143 8192 113.27874053199776
209 amc23_20 5 265 [1296, '1296'] True False 100 8192 143.99710955901537
210 amc23_32 3 11 [1, '1'] True False 80 8192 103.34868318098597
211 amc23_36 5 50 [50, '50'] True True 101 8192 93.4008934290614
212 amc23_25 1 7 [1/3.0, '1/3.'] True False 132 8192 116.14001861901488
213 amc23_33 6 18 [12.909*6.9, '12.909 * 6.9'] True False 101 8192 100.17435073200613
214 amc23_36 7 50 [50, '50'] True True 101 8192 93.00405342900194
215 amc23_33 5 18 [18, '18'] True True 101 8192 101.58143021399155
216 amc23_32 5 11 [101, '101'] True False 80 8193 105.08686058607418
217 amc23_29 4 13 [13, '13'] True True 149 8192 110.06985095702112
218 amc23_22 1 9 [372, '372'] True False 116 8192 128.46842872491106
219 amc23_32 2 11 [14, '14'] True False 80 8192 106.06993949599564
220 amc23_33 3 18 [18, '18'] True True 101 8192 104.67234957893379
221 amc23_20 0 265 [0, '0'] True False 100 8192 151.59554938203655
222 amc23_20 2 265 [3, '3'] True False 100 8192 149.26186313095968
223 amc23_36 2 50 [50, '50'] True True 101 8192 98.95953804405872
224 amc23_25 4 7 [1/6.0, '1/6.\n'] True False 132 8192 119.63788494304754
225 amc23_33 2 18 [6, '6'] True False 101 8192 106.19234514702111
226 amc23_25 3 7 [1/2.0, '1/2.'] True False 132 8192 121.71394772001076
227 amc23_30 6 5 [3, '3'] True False 52 8192 110.72991988004651
228 amc23_25 7 7 [35, '35'] True False 132 8192 122.51419615000486
229 amc23_25 0 7 [7, '7'] True True 132 8192 126.11816675704904
230 amc23_20 7 265 [15, '15'] True False 100 8192 155.29975685302634
231 amc23_30 2 5 [2, '2'] True False 52 8192 118.50598007801455
232 amc23_22 4 9 [2, '2'] True False 116 8192 137.73798931809142
233 amc23_30 7 5 [4, '4'] True False 52 8192 117.6527527780272
234 amc23_30 1 5 ['-1)\n'] True False 52 8191 120.94747834291775
235 amc23_33 4 18 [18, '18'] True True 101 8192 116.82629583601374
236 amc23_33 7 18 [18, '18'] True True 101 8192 114.88910927006509
237 amc23_28 6 50 [440, '440'] True False 97 8192 125.95157545409165
238 amc23_36 6 50 [50, '50'] True True 101 8192 108.96922374202404
239 amc23_25 2 7 [7, '7'] True True 132 8192 132.62190893501975
240 amc23_32 0 11 ['1*10 + 2*6 +'] True False 80 8193 123.44200975005515
241 amc23_30 3 5 [-3, '-3'] True False 52 8192 125.32482891203836
242 amc23_22 5 9 [0, '0'] True False 116 8192 147.18258160201367
243 amc23_27 6 13 [13, '13'] True True 91 8192 135.2919422989944
244 amc23_20 4 265 [3, '3'] True False 100 8192 169.53860774997156
245 amc23_36 1 50 [50, '50'] True True 101 8192 124.80863759992644
246 amc23_36 3 50 [50, '50'] True True 101 8192 123.346381515963
247 amc23_30 0 5 [24, '24'] True False 52 8190 134.52100193710066
248 amc23_30 5 5 [2, '2'] True False 52 8192 134.5675000550691
249 amc23_43 3 194 [194, '194'] True True 113 8192 76.50545846298337
250 amc23_44 0 1625 [1625, '1625'] True True 65 8192 73.72094948706217
251 amc23_44 7 1625 [1625, '1625'] True True 65 8192 68.99611517100129
252 amc23_43 5 194 [194, '194'] True True 113 8192 75.64769548899494
253 amc23_43 1 194 [194, '194'] True True 113 8192 81.87070783996023
254 amc23_44 2 1625 [1625, '1625'] True True 65 8192 74.75722070003394
255 amc23_30 4 5 [4, '4'] True False 52 8192 138.57616749301087
256 amc23_43 2 194 [194, '194'] True True 113 8192 81.25590009696316
257 amc23_44 4 1625 [1625, '1625'] True True 65 8192 74.51399209094234
258 amc23_43 7 194 [194, '194'] True True 113 8192 79.12258289707825
259 amc23_40 0 11 [12, '12'] True False 52 8192 127.7509328359738
260 amc23_40 5 11 [0, '0'] True False 52 8192 125.41851273609791
261 amc23_44 1 1625 [1625, '1625'] True True 65 8192 79.91086279402953
262 amc23_44 5 1625 [1625, '1625'] True True 65 8192 76.03660052805208
263 amc23_43 6 194 [194, '194'] True True 113 8192 82.76726872497238
264 amc23_44 3 1625 [1625, '1625'] True True 65 8192 80.81791399000213
265 amc23_43 4 194 [194, '194'] True True 113 8192 89.84170640306547
266 amc23_44 6 1625 [1625, '1625'] True True 65 8192 84.02751414501108
267 amc23_40 2 11 [6, '6'] True False 52 8192 136.47187170991674
268 amc23_40 7 11 [1, '1'] True False 52 8192 133.55518094298895
269 amc23_45 2 4 [3, '3'] True False 134 8192 85.19560115900822
270 amc23_41 1 3 [4, '4'] True False 232 8192 106.12409789999947
271 amc23_41 0 3 [2, '2'] True False 232 8192 109.99717283295467
272 amc23_47 6 901 [0, '0'] True False 72 8192 68.09748758305795
273 amc23_40 4 11 [5, '5'] True False 52 8192 146.58534501399845
274 amc23_43 0 194 [194, '194'] True True 113 8192 108.1631193900248
275 amc23_40 6 11 [3, '3'] True False 52 8192 146.67214590497315
276 amc23_41 2 3 [2, '2'] True False 232 8192 114.6246078920085
277 amc23_41 7 3 [2, '2'] True False 232 8192 113.28283428493887
278 amc23_40 1 11 ['0)\n'] True False 52 8192 153.70327479508705
279 amc23_41 3 3 [3, '3'] True True 232 8192 117.59636711794883
280 amc23_41 5 3 [4, '4'] True False 232 8192 121.3757939360803
281 amc23_41 6 3 [0, '0'] True False 232 8192 120.55719395296182
282 amc23_41 4 3 [3, '3'] True True 232 8192 127.00377039599698
283 amc23_40 3 11 [1, '1'] True False 52 8192 165.2669527590042
284 amc23_45 1 4 [8, '8'] True False 134 8192 111.99631542200223
285 amc23_47 2 901 [999, '999'] True False 72 8192 100.02184757392388
286 amc23_49 5 8 [2, '2'] True False 55 8192 89.85825391602702
287 amc23_46 1 6 [0, '0'] True False 99 8192 112.94967331597582
288 amc23_47 3 901 [999, '999'] True False 72 8192 105.72023175493814
289 amc23_48 0 144 [3, '3'] True False 92 8192 100.4109142839443
290 amc23_48 6 144 [144, '144'] True True 92 8192 99.23151853494346
291 amc23_47 0 901 [900, '900'] True False 72 8192 110.1760751530528
292 amc23_45 5 4 [3, '3'] True False 134 8192 118.01113523892127
293 amc23_46 2 6 [2, '2'] True False 99 8192 116.38127740600612
294 amc23_45 6 4 [6, '6'] True False 134 8192 119.06724345101975
295 amc23_48 2 144 ['1). \n'] True False 92 8192 103.23088083101902
296 amc23_46 3 6 [1, '1'] True False 99 8192 117.56262404005975
297 amc23_48 5 144 [1, '1'] True False 92 8192 104.18325246800669
298 amc23_48 4 144 [144, '144'] True True 92 8192 106.01285172509961
299 amc23_45 7 4 [2, '2'] True False 134 8192 122.03002966206986
300 amc23_47 7 901 ['3).'] True False 72 8192 107.72763259895146
301 amc23_49 1 8 [1, '1'] True False 55 8192 104.14076177403331
302 amc23_46 0 6 ['2)\n3. (2'] True False 99 8192 123.11878581799101
303 amc23_49 2 8 [2, '2'] True False 55 8192 104.14129159902222
304 amc23_49 4 8 [0, '0'] True False 55 8192 104.36290648498107
305 amc23_47 1 901 [100, '100'] True False 72 8192 116.60050178796519
306 amc23_46 7 6 [5, '5'] True False 99 8191 119.27038910891861
307 amc23_47 5 901 [999, '999'] True False 72 8192 112.39885503100231
308 amc23_48 1 144 ['1 ).'] True False 92 8192 110.12675413594116
309 amc23_45 3 4 [2, '2'] True False 134 8192 129.43085643602535
310 amc23_46 4 6 [3, '3'] True False 99 8192 124.42130887892563
311 amc23_47 4 901 [901, '901'] True True 72 8192 114.14520193496719
312 amc23_48 7 144 [233, '233'] True False 92 8192 108.05754708801396
313 amc23_49 0 8 ['0.5)\n\n-'] True False 55 8192 107.90004588407464
314 amc23_46 6 6 [11, '11'] True False 99 8192 121.42186184797902
315 amc23_46 5 6 [10, '10'] True False 99 8192 121.73959818901494
316 amc23_45 0 4 [3, '3'] True False 134 8192 133.02634463005234
317 amc23_49 6 8 [0, '0'] True False 55 8192 106.13942024903372
318 amc23_49 3 8 ['1).'] True False 55 8192 109.3490971380379
319 amc23_49 7 8 [0, '0'] True False 55 8192 107.16895192000084
320 amc23_45 4 4 [1, '1'] True False 134 8192 133.75850401399657
321 amc23_48 3 144 [0, '0'] True False 92 8192 118.62594668800011

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 8192
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 8
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,43 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
amc23_0,1.000,8,8,8192.00
amc23_11,1.000,8,8,8192.00
amc23_2,1.000,8,8,8192.00
amc23_1,0.625,5,8,8192.00
amc23_12,0.125,1,8,8192.00
amc23_3,1.000,8,8,8192.00
amc23_8,0.000,0,8,8192.00
amc23_5,0.625,5,8,8192.00
amc23_10,0.375,3,8,8192.00
amc23_16,0.000,0,8,8192.00
amc23_15,0.250,2,8,8192.00
amc23_17,0.125,1,8,8191.38
amc23_7,0.125,1,8,8192.00
amc23_4,0.125,1,8,8191.62
amc23_14,0.000,0,8,8192.00
amc23_13,0.000,0,8,8192.00
amc23_19,0.750,6,8,8192.00
amc23_18,1.000,8,8,8192.00
amc23_21,1.000,8,8,8192.00
amc23_22,0.000,0,8,8192.00
amc23_23,1.000,8,8,8192.00
amc23_26,0.750,6,8,8192.00
amc23_28,0.875,7,8,8192.00
amc23_29,0.750,6,8,8192.00
amc23_27,0.875,7,8,8192.00
amc23_25,0.500,4,8,8192.00
amc23_36,1.000,8,8,8192.00
amc23_33,0.750,6,8,8192.00
amc23_32,0.000,0,8,8192.25
amc23_20,0.000,0,8,8192.00
amc23_30,0.000,0,8,8191.62
amc23_43,1.000,8,8,8192.00
amc23_44,1.000,8,8,8192.00
amc23_40,0.000,0,8,8192.00
amc23_45,0.000,0,8,8192.00
amc23_41,0.250,2,8,8192.00
amc23_47,0.125,1,8,8192.00
amc23_49,0.000,0,8,8192.00
amc23_46,0.000,0,8,8191.88
amc23_48,0.250,2,8,8192.00
Total Accuracy,0.456,146,320,8191.97
1 problem_id accuracy correct_count total_samples avg_output_length
2 amc23_0 1.000 8 8 8192.00
3 amc23_11 1.000 8 8 8192.00
4 amc23_2 1.000 8 8 8192.00
5 amc23_1 0.625 5 8 8192.00
6 amc23_12 0.125 1 8 8192.00
7 amc23_3 1.000 8 8 8192.00
8 amc23_8 0.000 0 8 8192.00
9 amc23_5 0.625 5 8 8192.00
10 amc23_10 0.375 3 8 8192.00
11 amc23_16 0.000 0 8 8192.00
12 amc23_15 0.250 2 8 8192.00
13 amc23_17 0.125 1 8 8191.38
14 amc23_7 0.125 1 8 8192.00
15 amc23_4 0.125 1 8 8191.62
16 amc23_14 0.000 0 8 8192.00
17 amc23_13 0.000 0 8 8192.00
18 amc23_19 0.750 6 8 8192.00
19 amc23_18 1.000 8 8 8192.00
20 amc23_21 1.000 8 8 8192.00
21 amc23_22 0.000 0 8 8192.00
22 amc23_23 1.000 8 8 8192.00
23 amc23_26 0.750 6 8 8192.00
24 amc23_28 0.875 7 8 8192.00
25 amc23_29 0.750 6 8 8192.00
26 amc23_27 0.875 7 8 8192.00
27 amc23_25 0.500 4 8 8192.00
28 amc23_36 1.000 8 8 8192.00
29 amc23_33 0.750 6 8 8192.00
30 amc23_32 0.000 0 8 8192.25
31 amc23_20 0.000 0 8 8192.00
32 amc23_30 0.000 0 8 8191.62
33 amc23_43 1.000 8 8 8192.00
34 amc23_44 1.000 8 8 8192.00
35 amc23_40 0.000 0 8 8192.00
36 amc23_45 0.000 0 8 8192.00
37 amc23_41 0.250 2 8 8192.00
38 amc23_47 0.125 1 8 8192.00
39 amc23_49 0.000 0 8 8192.00
40 amc23_46 0.000 0 8 8191.88
41 amc23_48 0.250 2 8 8192.00
42 Total Accuracy 0.456 146 320 8191.97

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,1710464,65.2490234375
2,247565,9.443855285644531
3,127965,4.881477355957031
4,535446,20.425643920898438
Total Tokens,2621440,100.0
1 iter_count token_count percentage
2 1 1710464 65.2490234375
3 2 247565 9.443855285644531
4 3 127965 4.881477355957031
5 4 535446 20.425643920898438
6 Total Tokens 2621440 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@8": 0.7,
"cons@8": 0.55,
"avg@8": 0.4562,
"avg_output_length": 8191.97,
"num_problems": 40,
"num_samples": 320,
"repeat_size": 8,
"avg_request_time": 104.2308,
"end_2_end_time": 321.1005,
"token_throughtput": 8163.8914,
"request_throught": 0.9966,
"avg_iter_count": 1.8048,
"total_concurrency": 128,
"failed_requests": 0
}

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 8192
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 4
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,503 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
math500_math500_8,1.000,4,4,8192.00
math500_math500_31,1.000,4,4,8192.00
math500_math500_0,1.000,4,4,8192.00
math500_math500_20,1.000,4,4,8192.00
math500_math500_27,1.000,4,4,8192.00
math500_math500_29,1.000,4,4,8192.00
math500_math500_2,1.000,4,4,8192.00
math500_math500_3,1.000,4,4,8192.00
math500_math500_13,1.000,4,4,8192.00
math500_math500_23,1.000,4,4,8192.00
math500_math500_28,1.000,4,4,8192.00
math500_math500_30,1.000,4,4,8192.00
math500_math500_5,1.000,4,4,8192.00
math500_math500_4,0.500,2,4,8192.00
math500_math500_16,1.000,4,4,8192.00
math500_math500_12,1.000,4,4,8192.00
math500_math500_6,1.000,4,4,8192.00
math500_math500_14,1.000,4,4,8192.00
math500_math500_7,1.000,4,4,8192.00
math500_math500_24,1.000,4,4,8192.00
math500_math500_21,0.000,0,4,8192.00
math500_math500_22,0.750,3,4,8192.00
math500_math500_26,0.000,0,4,8192.00
math500_math500_1,0.250,1,4,8191.75
math500_math500_15,0.000,0,4,8192.00
math500_math500_25,0.750,3,4,8192.00
math500_math500_19,1.000,4,4,8192.00
math500_math500_10,1.000,4,4,8192.00
math500_math500_9,0.000,0,4,8192.00
math500_math500_11,0.000,0,4,8192.00
math500_math500_18,0.000,0,4,8192.00
math500_math500_17,0.750,3,4,8192.00
math500_math500_35,1.000,4,4,8192.00
math500_math500_38,1.000,4,4,8192.00
math500_math500_34,0.750,3,4,8192.00
math500_math500_33,1.000,4,4,8192.00
math500_math500_42,1.000,4,4,8192.00
math500_math500_39,1.000,4,4,8192.00
math500_math500_36,0.750,3,4,8192.00
math500_math500_40,1.000,4,4,8192.00
math500_math500_37,1.000,4,4,8192.00
math500_math500_49,1.000,4,4,8192.00
math500_math500_45,1.000,4,4,8192.00
math500_math500_48,1.000,4,4,8192.00
math500_math500_47,1.000,4,4,8192.00
math500_math500_44,1.000,4,4,8192.00
math500_math500_32,0.000,0,4,8192.00
math500_math500_54,1.000,4,4,8192.00
math500_math500_53,1.000,4,4,8192.00
math500_math500_55,1.000,4,4,8192.00
math500_math500_51,0.750,3,4,8192.00
math500_math500_57,1.000,4,4,8192.00
math500_math500_56,1.000,4,4,8192.00
math500_math500_58,1.000,4,4,8192.00
math500_math500_52,0.750,3,4,8192.00
math500_math500_46,0.500,2,4,8192.00
math500_math500_59,1.000,4,4,8192.00
math500_math500_41,0.250,1,4,8192.00
math500_math500_43,0.000,0,4,8192.00
math500_math500_50,0.500,2,4,8192.00
math500_math500_61,1.000,4,4,8192.00
math500_math500_62,0.750,3,4,8192.00
math500_math500_65,1.000,4,4,8192.00
math500_math500_60,0.000,0,4,8192.00
math500_math500_66,1.000,4,4,8192.00
math500_math500_67,1.000,4,4,8192.00
math500_math500_70,1.000,4,4,8192.00
math500_math500_63,0.500,2,4,8192.00
math500_math500_64,0.250,1,4,8192.00
math500_math500_69,1.000,4,4,8192.00
math500_math500_77,1.000,4,4,8192.00
math500_math500_72,1.000,4,4,8191.75
math500_math500_73,1.000,4,4,8192.00
math500_math500_79,1.000,4,4,8192.00
math500_math500_78,0.750,3,4,8192.00
math500_math500_75,1.000,4,4,8192.00
math500_math500_74,1.000,4,4,8192.00
math500_math500_68,0.000,0,4,8192.00
math500_math500_71,0.000,0,4,8192.00
math500_math500_85,0.750,3,4,8192.00
math500_math500_81,1.000,4,4,8192.00
math500_math500_86,1.000,4,4,8192.00
math500_math500_87,1.000,4,4,8192.00
math500_math500_84,0.750,3,4,8192.00
math500_math500_83,1.000,4,4,8192.00
math500_math500_89,1.000,4,4,8192.00
math500_math500_76,1.000,4,4,8192.00
math500_math500_90,0.000,0,4,8192.00
math500_math500_93,1.000,4,4,8192.00
math500_math500_95,1.000,4,4,8192.00
math500_math500_82,0.250,1,4,8192.00
math500_math500_80,0.000,0,4,8192.00
math500_math500_91,1.000,4,4,8193.00
math500_math500_98,1.000,4,4,8192.00
math500_math500_99,1.000,4,4,8192.00
math500_math500_94,0.000,0,4,8192.00
math500_math500_105,0.750,3,4,8192.00
math500_math500_92,1.000,4,4,8192.00
math500_math500_97,0.750,3,4,8192.00
math500_math500_101,0.000,0,4,8191.75
math500_math500_102,1.000,4,4,8192.00
math500_math500_88,0.250,1,4,8192.00
math500_math500_107,1.000,4,4,8192.00
math500_math500_111,1.000,4,4,8191.75
math500_math500_96,0.000,0,4,8192.00
math500_math500_106,1.000,4,4,8192.00
math500_math500_109,1.000,4,4,8192.00
math500_math500_103,0.000,0,4,8192.00
math500_math500_113,0.750,3,4,8192.00
math500_math500_117,1.000,4,4,8192.00
math500_math500_115,0.750,3,4,8192.00
math500_math500_104,0.500,2,4,8192.00
math500_math500_114,1.000,4,4,8192.00
math500_math500_121,1.000,4,4,8192.00
math500_math500_116,1.000,4,4,8192.00
math500_math500_110,0.000,0,4,8192.00
math500_math500_108,0.250,1,4,8192.00
math500_math500_100,0.000,0,4,8192.00
math500_math500_112,1.000,4,4,8192.00
math500_math500_122,1.000,4,4,8192.00
math500_math500_125,1.000,4,4,8192.00
math500_math500_127,1.000,4,4,8191.75
math500_math500_119,0.000,0,4,8192.00
math500_math500_124,1.000,4,4,8192.00
math500_math500_120,0.250,1,4,8192.00
math500_math500_123,1.000,4,4,8192.00
math500_math500_131,1.000,4,4,8192.00
math500_math500_133,1.000,4,4,8192.00
math500_math500_128,0.750,3,4,8192.00
math500_math500_135,1.000,4,4,8192.00
math500_math500_126,0.000,0,4,8192.00
math500_math500_118,0.000,0,4,8192.00
math500_math500_137,0.750,3,4,8192.00
math500_math500_129,0.250,1,4,8192.00
math500_math500_132,1.000,4,4,8192.00
math500_math500_134,1.000,4,4,8192.00
math500_math500_143,1.000,4,4,8192.00
math500_math500_144,1.000,4,4,8192.00
math500_math500_130,0.250,1,4,8192.00
math500_math500_140,1.000,4,4,8192.00
math500_math500_141,1.000,4,4,8192.00
math500_math500_146,1.000,4,4,8192.00
math500_math500_139,0.750,3,4,8192.00
math500_math500_148,1.000,4,4,8192.00
math500_math500_136,0.250,1,4,8192.00
math500_math500_138,0.000,0,4,8192.00
math500_math500_145,0.250,1,4,8192.00
math500_math500_149,1.000,4,4,8192.00
math500_math500_147,0.250,1,4,8192.00
math500_math500_152,0.500,2,4,8150.00
math500_math500_150,0.500,2,4,8192.00
math500_math500_161,1.000,4,4,8192.00
math500_math500_159,1.000,4,4,8192.00
math500_math500_151,0.250,1,4,8191.50
math500_math500_160,1.000,4,4,8192.00
math500_math500_142,0.500,2,4,8192.00
math500_math500_157,1.000,4,4,8192.00
math500_math500_158,1.000,4,4,8192.00
math500_math500_155,1.000,4,4,8192.00
math500_math500_165,0.750,3,4,8192.00
math500_math500_167,1.000,4,4,8192.00
math500_math500_162,1.000,4,4,8192.00
math500_math500_153,0.250,1,4,8192.00
math500_math500_154,0.000,0,4,8191.75
math500_math500_169,1.000,4,4,8192.00
math500_math500_163,0.750,3,4,8192.00
math500_math500_156,0.000,0,4,8192.00
math500_math500_171,1.000,4,4,8192.00
math500_math500_172,1.000,4,4,8192.00
math500_math500_164,0.750,3,4,8192.00
math500_math500_177,0.250,1,4,8192.00
math500_math500_174,1.000,4,4,8192.00
math500_math500_175,1.000,4,4,8192.00
math500_math500_166,0.000,0,4,8192.00
math500_math500_173,1.000,4,4,8192.00
math500_math500_170,0.500,2,4,8192.00
math500_math500_179,0.750,3,4,8192.00
math500_math500_182,1.000,4,4,8192.00
math500_math500_185,1.000,4,4,8192.00
math500_math500_178,1.000,4,4,8192.00
math500_math500_181,1.000,4,4,8192.50
math500_math500_168,0.000,0,4,8192.00
math500_math500_183,1.000,4,4,8192.00
math500_math500_187,1.000,4,4,8192.00
math500_math500_176,0.750,3,4,8192.00
math500_math500_191,1.000,4,4,8192.00
math500_math500_180,1.000,4,4,8192.00
math500_math500_190,0.750,3,4,8192.00
math500_math500_192,1.000,4,4,8192.00
math500_math500_193,0.750,3,4,8192.00
math500_math500_199,1.000,4,4,8192.00
math500_math500_195,1.000,4,4,8192.00
math500_math500_186,1.000,4,4,8192.00
math500_math500_196,1.000,4,4,8192.00
math500_math500_184,0.000,0,4,8192.00
math500_math500_188,1.000,4,4,8193.00
math500_math500_189,0.500,2,4,8192.00
math500_math500_198,0.500,2,4,8191.75
math500_math500_200,1.000,4,4,8189.75
math500_math500_194,0.250,1,4,8192.00
math500_math500_207,1.000,4,4,8192.00
math500_math500_206,1.000,4,4,8192.00
math500_math500_201,0.750,3,4,8192.00
math500_math500_197,0.750,3,4,8192.00
math500_math500_209,0.750,3,4,8192.00
math500_math500_203,0.750,3,4,8192.00
math500_math500_211,1.000,4,4,8192.00
math500_math500_212,1.000,4,4,8192.00
math500_math500_208,1.000,4,4,8192.00
math500_math500_205,0.500,2,4,8192.00
math500_math500_215,1.000,4,4,8192.00
math500_math500_204,0.000,0,4,8192.00
math500_math500_216,1.000,4,4,8192.00
math500_math500_213,0.750,3,4,8192.00
math500_math500_218,1.000,4,4,8192.00
math500_math500_202,0.750,3,4,8192.00
math500_math500_214,0.000,0,4,8192.00
math500_math500_220,1.000,4,4,8192.00
math500_math500_225,1.000,4,4,8192.00
math500_math500_217,0.000,0,4,8192.00
math500_math500_210,1.000,4,4,8192.00
math500_math500_223,0.000,0,4,8192.00
math500_math500_227,1.000,4,4,8192.00
math500_math500_229,1.000,4,4,8192.00
math500_math500_231,1.000,4,4,8192.00
math500_math500_221,1.000,4,4,8192.00
math500_math500_235,0.750,3,4,8192.00
math500_math500_219,0.250,1,4,8191.75
math500_math500_226,1.000,4,4,8192.00
math500_math500_224,0.000,0,4,8192.00
math500_math500_228,0.500,2,4,8192.00
math500_math500_233,1.000,4,4,8192.00
math500_math500_237,1.000,4,4,8192.00
math500_math500_222,0.250,1,4,8192.00
math500_math500_234,1.000,4,4,8192.00
math500_math500_243,1.000,4,4,8192.00
math500_math500_238,1.000,4,4,8192.00
math500_math500_241,1.000,4,4,8192.00
math500_math500_230,1.000,4,4,8192.00
math500_math500_236,0.500,2,4,8192.00
math500_math500_247,1.000,4,4,8192.00
math500_math500_232,0.000,0,4,8192.00
math500_math500_239,0.000,0,4,8191.75
math500_math500_253,1.000,4,4,8192.00
math500_math500_250,1.000,4,4,8192.00
math500_math500_245,0.250,1,4,8192.00
math500_math500_242,0.000,0,4,8192.00
math500_math500_244,1.000,4,4,8192.00
math500_math500_257,1.000,4,4,8192.00
math500_math500_259,0.750,3,4,8192.00
math500_math500_240,0.000,0,4,8192.00
math500_math500_246,0.500,2,4,8192.00
math500_math500_251,1.000,4,4,8192.00
math500_math500_255,1.000,4,4,8192.00
math500_math500_252,1.000,4,4,8192.00
math500_math500_249,0.500,2,4,8192.00
math500_math500_258,1.000,4,4,8192.00
math500_math500_256,1.000,4,4,8192.00
math500_math500_248,0.000,0,4,8193.00
math500_math500_263,1.000,4,4,8192.00
math500_math500_261,0.750,3,4,8192.00
math500_math500_260,1.000,4,4,8192.00
math500_math500_254,0.750,3,4,8192.00
math500_math500_265,1.000,4,4,8192.00
math500_math500_262,1.000,4,4,8192.00
math500_math500_269,0.750,3,4,8192.00
math500_math500_270,1.000,4,4,8192.00
math500_math500_266,1.000,4,4,8192.00
math500_math500_271,1.000,4,4,8192.00
math500_math500_268,1.000,4,4,8192.00
math500_math500_275,1.000,4,4,8192.00
math500_math500_273,1.000,4,4,8192.00
math500_math500_277,1.000,4,4,8192.00
math500_math500_272,0.750,3,4,8192.00
math500_math500_278,1.000,4,4,8192.00
math500_math500_283,1.000,4,4,8192.00
math500_math500_267,0.000,0,4,8191.75
math500_math500_280,1.000,4,4,8192.00
math500_math500_279,0.250,1,4,8192.00
math500_math500_264,0.000,0,4,8192.00
math500_math500_276,1.000,4,4,8192.00
math500_math500_287,0.750,3,4,8192.00
math500_math500_290,1.000,4,4,8192.00
math500_math500_285,0.250,1,4,8192.00
math500_math500_274,0.000,0,4,8192.00
math500_math500_282,0.500,2,4,8192.00
math500_math500_293,1.000,4,4,8192.00
math500_math500_281,0.000,0,4,8192.00
math500_math500_284,0.250,1,4,8192.00
math500_math500_289,0.750,3,4,8192.00
math500_math500_286,0.000,0,4,8192.00
math500_math500_292,0.500,2,4,8192.00
math500_math500_297,1.000,4,4,8192.00
math500_math500_298,0.750,3,4,8192.00
math500_math500_291,0.750,3,4,8192.00
math500_math500_288,0.250,1,4,8192.00
math500_math500_294,0.750,3,4,8192.00
math500_math500_295,0.000,0,4,8192.00
math500_math500_299,1.000,4,4,8192.00
math500_math500_304,1.000,4,4,8192.00
math500_math500_305,1.000,4,4,8192.00
math500_math500_300,1.000,4,4,8192.00
math500_math500_296,0.250,1,4,8192.00
math500_math500_302,0.250,1,4,8192.00
math500_math500_307,0.250,1,4,8192.00
math500_math500_301,0.750,3,4,8192.00
math500_math500_309,0.000,0,4,8192.00
math500_math500_303,0.500,2,4,8192.00
math500_math500_312,1.000,4,4,8192.00
math500_math500_310,1.000,4,4,8192.00
math500_math500_313,1.000,4,4,8192.00
math500_math500_314,1.000,4,4,8192.00
math500_math500_319,1.000,4,4,8192.00
math500_math500_311,0.750,3,4,8192.00
math500_math500_315,1.000,4,4,8192.00
math500_math500_316,1.000,4,4,8192.00
math500_math500_321,1.000,4,4,8192.00
math500_math500_306,0.000,0,4,8192.00
math500_math500_322,1.000,4,4,8192.00
math500_math500_325,1.000,4,4,8192.00
math500_math500_308,0.000,0,4,8192.00
math500_math500_318,1.000,4,4,8192.00
math500_math500_317,0.750,3,4,8192.00
math500_math500_329,1.000,4,4,8192.00
math500_math500_332,0.750,3,4,8192.00
math500_math500_320,0.250,1,4,8192.00
math500_math500_330,1.000,4,4,8192.00
math500_math500_331,1.000,4,4,8192.00
math500_math500_327,0.000,0,4,8192.00
math500_math500_335,0.750,3,4,8192.00
math500_math500_336,1.000,4,4,8192.00
math500_math500_326,1.000,4,4,8192.00
math500_math500_334,0.750,3,4,8192.00
math500_math500_324,0.000,0,4,8192.00
math500_math500_328,0.250,1,4,8192.50
math500_math500_338,1.000,4,4,8192.00
math500_math500_323,0.250,1,4,8192.00
math500_math500_333,0.250,1,4,8192.00
math500_math500_337,1.000,4,4,8192.00
math500_math500_345,0.750,3,4,8192.00
math500_math500_343,1.000,4,4,8192.00
math500_math500_341,1.000,4,4,8192.00
math500_math500_344,1.000,4,4,8192.00
math500_math500_339,1.000,4,4,8192.00
math500_math500_342,1.000,4,4,8192.00
math500_math500_347,1.000,4,4,8192.00
math500_math500_353,1.000,4,4,8192.00
math500_math500_340,0.000,0,4,8192.00
math500_math500_350,1.000,4,4,8192.00
math500_math500_348,0.750,3,4,8192.00
math500_math500_354,1.000,4,4,8192.00
math500_math500_346,0.750,3,4,8192.00
math500_math500_351,0.250,1,4,8192.00
math500_math500_356,1.000,4,4,8192.00
math500_math500_358,0.500,2,4,8192.00
math500_math500_363,1.000,4,4,8192.00
math500_math500_359,0.500,2,4,8191.75
math500_math500_352,0.000,0,4,8192.00
math500_math500_357,1.000,4,4,8191.75
math500_math500_367,1.000,4,4,8192.00
math500_math500_355,0.000,0,4,8192.00
math500_math500_364,0.750,3,4,8192.00
math500_math500_360,1.000,4,4,8192.00
math500_math500_362,1.000,4,4,8192.00
math500_math500_370,1.000,4,4,8192.00
math500_math500_349,0.250,1,4,8192.00
math500_math500_368,1.000,4,4,8192.00
math500_math500_361,0.000,0,4,8192.00
math500_math500_366,1.000,4,4,8192.00
math500_math500_374,1.000,4,4,8192.00
math500_math500_376,1.000,4,4,8192.00
math500_math500_373,1.000,4,4,8192.00
math500_math500_378,1.000,4,4,8192.00
math500_math500_365,0.250,1,4,8192.00
math500_math500_384,1.000,4,4,8192.00
math500_math500_369,0.000,0,4,8192.00
math500_math500_383,1.000,4,4,8192.00
math500_math500_375,1.000,4,4,8192.00
math500_math500_372,0.500,2,4,8191.25
math500_math500_371,0.000,0,4,8192.00
math500_math500_380,0.250,1,4,8192.00
math500_math500_379,1.000,4,4,8192.00
math500_math500_388,1.000,4,4,8192.00
math500_math500_386,1.000,4,4,8192.00
math500_math500_387,1.000,4,4,8192.00
math500_math500_382,0.500,2,4,8192.00
math500_math500_385,0.750,3,4,8192.00
math500_math500_377,0.500,2,4,8198.75
math500_math500_389,1.000,4,4,8192.00
math500_math500_393,1.000,4,4,8192.00
math500_math500_381,0.000,0,4,8192.00
math500_math500_397,1.000,4,4,8192.00
math500_math500_395,1.000,4,4,8192.00
math500_math500_390,0.500,2,4,8192.00
math500_math500_398,0.750,3,4,8192.00
math500_math500_392,0.000,0,4,8192.00
math500_math500_394,0.500,2,4,8192.00
math500_math500_391,1.000,4,4,8192.00
math500_math500_399,1.000,4,4,8192.00
math500_math500_402,0.500,2,4,8192.00
math500_math500_404,1.000,4,4,8192.00
math500_math500_406,1.000,4,4,8192.00
math500_math500_407,1.000,4,4,8192.00
math500_math500_405,1.000,4,4,8192.00
math500_math500_403,0.000,0,4,8192.00
math500_math500_410,1.000,4,4,8192.00
math500_math500_396,1.000,4,4,8192.00
math500_math500_400,0.000,0,4,8192.00
math500_math500_409,1.000,4,4,8192.00
math500_math500_411,1.000,4,4,8192.00
math500_math500_414,1.000,4,4,8193.00
math500_math500_413,1.000,4,4,8192.00
math500_math500_401,0.250,1,4,8191.75
math500_math500_415,1.000,4,4,8192.00
math500_math500_408,0.250,1,4,8192.00
math500_math500_417,1.000,4,4,8192.00
math500_math500_418,1.000,4,4,8192.00
math500_math500_420,1.000,4,4,8197.50
math500_math500_424,1.000,4,4,8192.00
math500_math500_427,1.000,4,4,8192.00
math500_math500_416,0.500,2,4,8192.00
math500_math500_412,0.000,0,4,8192.00
math500_math500_426,1.000,4,4,8192.00
math500_math500_421,0.000,0,4,8192.00
math500_math500_430,1.000,4,4,8192.00
math500_math500_429,1.000,4,4,8192.00
math500_math500_422,0.000,0,4,8191.25
math500_math500_423,1.000,4,4,8192.00
math500_math500_419,0.250,1,4,8192.00
math500_math500_431,1.000,4,4,8192.00
math500_math500_433,1.000,4,4,8192.00
math500_math500_428,1.000,4,4,8192.00
math500_math500_425,0.000,0,4,8192.00
math500_math500_435,1.000,4,4,8192.00
math500_math500_434,1.000,4,4,8192.00
math500_math500_440,1.000,4,4,8192.00
math500_math500_441,1.000,4,4,8192.00
math500_math500_432,0.000,0,4,8192.00
math500_math500_436,0.750,3,4,8192.00
math500_math500_443,1.000,4,4,8192.00
math500_math500_437,1.000,4,4,8192.00
math500_math500_442,1.000,4,4,8192.00
math500_math500_438,1.000,4,4,8192.00
math500_math500_439,0.500,2,4,8192.00
math500_math500_447,1.000,4,4,8192.00
math500_math500_446,0.750,3,4,8192.00
math500_math500_449,1.000,4,4,8192.00
math500_math500_448,1.000,4,4,8192.00
math500_math500_453,1.000,4,4,8192.00
math500_math500_455,1.000,4,4,8192.00
math500_math500_445,0.500,2,4,8192.00
math500_math500_452,1.000,4,4,8192.00
math500_math500_450,1.000,4,4,8192.00
math500_math500_456,0.750,3,4,8192.00
math500_math500_444,0.000,0,4,8192.00
math500_math500_454,0.750,3,4,8192.00
math500_math500_457,1.000,4,4,8192.00
math500_math500_451,1.000,4,4,8192.00
math500_math500_461,0.750,3,4,8192.00
math500_math500_463,1.000,4,4,8192.00
math500_math500_458,0.750,3,4,8192.00
math500_math500_465,1.000,4,4,8192.00
math500_math500_464,1.000,4,4,8192.00
math500_math500_471,1.000,4,4,8192.00
math500_math500_459,1.000,4,4,8192.00
math500_math500_468,1.000,4,4,8192.00
math500_math500_472,1.000,4,4,8192.00
math500_math500_469,1.000,4,4,8192.00
math500_math500_467,0.750,3,4,8192.00
math500_math500_460,0.000,0,4,8192.25
math500_math500_462,0.500,2,4,8191.00
math500_math500_474,0.750,3,4,8192.00
math500_math500_466,0.000,0,4,8192.00
math500_math500_476,1.000,4,4,8192.00
math500_math500_477,1.000,4,4,8192.00
math500_math500_473,0.750,3,4,8192.00
math500_math500_479,1.000,4,4,8192.00
math500_math500_483,1.000,4,4,8192.00
math500_math500_470,0.250,1,4,8190.50
math500_math500_487,1.000,4,4,8192.00
math500_math500_475,0.000,0,4,8192.00
math500_math500_485,0.500,2,4,8192.00
math500_math500_480,1.000,4,4,8192.00
math500_math500_488,1.000,4,4,8192.00
math500_math500_484,1.000,4,4,8192.00
math500_math500_478,0.000,0,4,8192.00
math500_math500_481,0.000,0,4,8192.00
math500_math500_482,0.500,2,4,8192.00
math500_math500_492,1.000,4,4,8192.00
math500_math500_490,0.250,1,4,8192.00
math500_math500_486,0.750,3,4,8192.00
math500_math500_493,0.750,3,4,8192.00
math500_math500_495,1.000,4,4,8192.00
math500_math500_496,1.000,4,4,8192.00
math500_math500_489,1.000,4,4,8192.00
math500_math500_499,0.750,3,4,8192.00
math500_math500_498,1.000,4,4,8192.00
math500_math500_491,0.250,1,4,8192.00
math500_math500_497,0.000,0,4,8192.00
math500_math500_494,0.000,0,4,8192.00
Total Accuracy,0.730,1460,2000,8191.93
1 problem_id accuracy correct_count total_samples avg_output_length
2 math500_math500_8 1.000 4 4 8192.00
3 math500_math500_31 1.000 4 4 8192.00
4 math500_math500_0 1.000 4 4 8192.00
5 math500_math500_20 1.000 4 4 8192.00
6 math500_math500_27 1.000 4 4 8192.00
7 math500_math500_29 1.000 4 4 8192.00
8 math500_math500_2 1.000 4 4 8192.00
9 math500_math500_3 1.000 4 4 8192.00
10 math500_math500_13 1.000 4 4 8192.00
11 math500_math500_23 1.000 4 4 8192.00
12 math500_math500_28 1.000 4 4 8192.00
13 math500_math500_30 1.000 4 4 8192.00
14 math500_math500_5 1.000 4 4 8192.00
15 math500_math500_4 0.500 2 4 8192.00
16 math500_math500_16 1.000 4 4 8192.00
17 math500_math500_12 1.000 4 4 8192.00
18 math500_math500_6 1.000 4 4 8192.00
19 math500_math500_14 1.000 4 4 8192.00
20 math500_math500_7 1.000 4 4 8192.00
21 math500_math500_24 1.000 4 4 8192.00
22 math500_math500_21 0.000 0 4 8192.00
23 math500_math500_22 0.750 3 4 8192.00
24 math500_math500_26 0.000 0 4 8192.00
25 math500_math500_1 0.250 1 4 8191.75
26 math500_math500_15 0.000 0 4 8192.00
27 math500_math500_25 0.750 3 4 8192.00
28 math500_math500_19 1.000 4 4 8192.00
29 math500_math500_10 1.000 4 4 8192.00
30 math500_math500_9 0.000 0 4 8192.00
31 math500_math500_11 0.000 0 4 8192.00
32 math500_math500_18 0.000 0 4 8192.00
33 math500_math500_17 0.750 3 4 8192.00
34 math500_math500_35 1.000 4 4 8192.00
35 math500_math500_38 1.000 4 4 8192.00
36 math500_math500_34 0.750 3 4 8192.00
37 math500_math500_33 1.000 4 4 8192.00
38 math500_math500_42 1.000 4 4 8192.00
39 math500_math500_39 1.000 4 4 8192.00
40 math500_math500_36 0.750 3 4 8192.00
41 math500_math500_40 1.000 4 4 8192.00
42 math500_math500_37 1.000 4 4 8192.00
43 math500_math500_49 1.000 4 4 8192.00
44 math500_math500_45 1.000 4 4 8192.00
45 math500_math500_48 1.000 4 4 8192.00
46 math500_math500_47 1.000 4 4 8192.00
47 math500_math500_44 1.000 4 4 8192.00
48 math500_math500_32 0.000 0 4 8192.00
49 math500_math500_54 1.000 4 4 8192.00
50 math500_math500_53 1.000 4 4 8192.00
51 math500_math500_55 1.000 4 4 8192.00
52 math500_math500_51 0.750 3 4 8192.00
53 math500_math500_57 1.000 4 4 8192.00
54 math500_math500_56 1.000 4 4 8192.00
55 math500_math500_58 1.000 4 4 8192.00
56 math500_math500_52 0.750 3 4 8192.00
57 math500_math500_46 0.500 2 4 8192.00
58 math500_math500_59 1.000 4 4 8192.00
59 math500_math500_41 0.250 1 4 8192.00
60 math500_math500_43 0.000 0 4 8192.00
61 math500_math500_50 0.500 2 4 8192.00
62 math500_math500_61 1.000 4 4 8192.00
63 math500_math500_62 0.750 3 4 8192.00
64 math500_math500_65 1.000 4 4 8192.00
65 math500_math500_60 0.000 0 4 8192.00
66 math500_math500_66 1.000 4 4 8192.00
67 math500_math500_67 1.000 4 4 8192.00
68 math500_math500_70 1.000 4 4 8192.00
69 math500_math500_63 0.500 2 4 8192.00
70 math500_math500_64 0.250 1 4 8192.00
71 math500_math500_69 1.000 4 4 8192.00
72 math500_math500_77 1.000 4 4 8192.00
73 math500_math500_72 1.000 4 4 8191.75
74 math500_math500_73 1.000 4 4 8192.00
75 math500_math500_79 1.000 4 4 8192.00
76 math500_math500_78 0.750 3 4 8192.00
77 math500_math500_75 1.000 4 4 8192.00
78 math500_math500_74 1.000 4 4 8192.00
79 math500_math500_68 0.000 0 4 8192.00
80 math500_math500_71 0.000 0 4 8192.00
81 math500_math500_85 0.750 3 4 8192.00
82 math500_math500_81 1.000 4 4 8192.00
83 math500_math500_86 1.000 4 4 8192.00
84 math500_math500_87 1.000 4 4 8192.00
85 math500_math500_84 0.750 3 4 8192.00
86 math500_math500_83 1.000 4 4 8192.00
87 math500_math500_89 1.000 4 4 8192.00
88 math500_math500_76 1.000 4 4 8192.00
89 math500_math500_90 0.000 0 4 8192.00
90 math500_math500_93 1.000 4 4 8192.00
91 math500_math500_95 1.000 4 4 8192.00
92 math500_math500_82 0.250 1 4 8192.00
93 math500_math500_80 0.000 0 4 8192.00
94 math500_math500_91 1.000 4 4 8193.00
95 math500_math500_98 1.000 4 4 8192.00
96 math500_math500_99 1.000 4 4 8192.00
97 math500_math500_94 0.000 0 4 8192.00
98 math500_math500_105 0.750 3 4 8192.00
99 math500_math500_92 1.000 4 4 8192.00
100 math500_math500_97 0.750 3 4 8192.00
101 math500_math500_101 0.000 0 4 8191.75
102 math500_math500_102 1.000 4 4 8192.00
103 math500_math500_88 0.250 1 4 8192.00
104 math500_math500_107 1.000 4 4 8192.00
105 math500_math500_111 1.000 4 4 8191.75
106 math500_math500_96 0.000 0 4 8192.00
107 math500_math500_106 1.000 4 4 8192.00
108 math500_math500_109 1.000 4 4 8192.00
109 math500_math500_103 0.000 0 4 8192.00
110 math500_math500_113 0.750 3 4 8192.00
111 math500_math500_117 1.000 4 4 8192.00
112 math500_math500_115 0.750 3 4 8192.00
113 math500_math500_104 0.500 2 4 8192.00
114 math500_math500_114 1.000 4 4 8192.00
115 math500_math500_121 1.000 4 4 8192.00
116 math500_math500_116 1.000 4 4 8192.00
117 math500_math500_110 0.000 0 4 8192.00
118 math500_math500_108 0.250 1 4 8192.00
119 math500_math500_100 0.000 0 4 8192.00
120 math500_math500_112 1.000 4 4 8192.00
121 math500_math500_122 1.000 4 4 8192.00
122 math500_math500_125 1.000 4 4 8192.00
123 math500_math500_127 1.000 4 4 8191.75
124 math500_math500_119 0.000 0 4 8192.00
125 math500_math500_124 1.000 4 4 8192.00
126 math500_math500_120 0.250 1 4 8192.00
127 math500_math500_123 1.000 4 4 8192.00
128 math500_math500_131 1.000 4 4 8192.00
129 math500_math500_133 1.000 4 4 8192.00
130 math500_math500_128 0.750 3 4 8192.00
131 math500_math500_135 1.000 4 4 8192.00
132 math500_math500_126 0.000 0 4 8192.00
133 math500_math500_118 0.000 0 4 8192.00
134 math500_math500_137 0.750 3 4 8192.00
135 math500_math500_129 0.250 1 4 8192.00
136 math500_math500_132 1.000 4 4 8192.00
137 math500_math500_134 1.000 4 4 8192.00
138 math500_math500_143 1.000 4 4 8192.00
139 math500_math500_144 1.000 4 4 8192.00
140 math500_math500_130 0.250 1 4 8192.00
141 math500_math500_140 1.000 4 4 8192.00
142 math500_math500_141 1.000 4 4 8192.00
143 math500_math500_146 1.000 4 4 8192.00
144 math500_math500_139 0.750 3 4 8192.00
145 math500_math500_148 1.000 4 4 8192.00
146 math500_math500_136 0.250 1 4 8192.00
147 math500_math500_138 0.000 0 4 8192.00
148 math500_math500_145 0.250 1 4 8192.00
149 math500_math500_149 1.000 4 4 8192.00
150 math500_math500_147 0.250 1 4 8192.00
151 math500_math500_152 0.500 2 4 8150.00
152 math500_math500_150 0.500 2 4 8192.00
153 math500_math500_161 1.000 4 4 8192.00
154 math500_math500_159 1.000 4 4 8192.00
155 math500_math500_151 0.250 1 4 8191.50
156 math500_math500_160 1.000 4 4 8192.00
157 math500_math500_142 0.500 2 4 8192.00
158 math500_math500_157 1.000 4 4 8192.00
159 math500_math500_158 1.000 4 4 8192.00
160 math500_math500_155 1.000 4 4 8192.00
161 math500_math500_165 0.750 3 4 8192.00
162 math500_math500_167 1.000 4 4 8192.00
163 math500_math500_162 1.000 4 4 8192.00
164 math500_math500_153 0.250 1 4 8192.00
165 math500_math500_154 0.000 0 4 8191.75
166 math500_math500_169 1.000 4 4 8192.00
167 math500_math500_163 0.750 3 4 8192.00
168 math500_math500_156 0.000 0 4 8192.00
169 math500_math500_171 1.000 4 4 8192.00
170 math500_math500_172 1.000 4 4 8192.00
171 math500_math500_164 0.750 3 4 8192.00
172 math500_math500_177 0.250 1 4 8192.00
173 math500_math500_174 1.000 4 4 8192.00
174 math500_math500_175 1.000 4 4 8192.00
175 math500_math500_166 0.000 0 4 8192.00
176 math500_math500_173 1.000 4 4 8192.00
177 math500_math500_170 0.500 2 4 8192.00
178 math500_math500_179 0.750 3 4 8192.00
179 math500_math500_182 1.000 4 4 8192.00
180 math500_math500_185 1.000 4 4 8192.00
181 math500_math500_178 1.000 4 4 8192.00
182 math500_math500_181 1.000 4 4 8192.50
183 math500_math500_168 0.000 0 4 8192.00
184 math500_math500_183 1.000 4 4 8192.00
185 math500_math500_187 1.000 4 4 8192.00
186 math500_math500_176 0.750 3 4 8192.00
187 math500_math500_191 1.000 4 4 8192.00
188 math500_math500_180 1.000 4 4 8192.00
189 math500_math500_190 0.750 3 4 8192.00
190 math500_math500_192 1.000 4 4 8192.00
191 math500_math500_193 0.750 3 4 8192.00
192 math500_math500_199 1.000 4 4 8192.00
193 math500_math500_195 1.000 4 4 8192.00
194 math500_math500_186 1.000 4 4 8192.00
195 math500_math500_196 1.000 4 4 8192.00
196 math500_math500_184 0.000 0 4 8192.00
197 math500_math500_188 1.000 4 4 8193.00
198 math500_math500_189 0.500 2 4 8192.00
199 math500_math500_198 0.500 2 4 8191.75
200 math500_math500_200 1.000 4 4 8189.75
201 math500_math500_194 0.250 1 4 8192.00
202 math500_math500_207 1.000 4 4 8192.00
203 math500_math500_206 1.000 4 4 8192.00
204 math500_math500_201 0.750 3 4 8192.00
205 math500_math500_197 0.750 3 4 8192.00
206 math500_math500_209 0.750 3 4 8192.00
207 math500_math500_203 0.750 3 4 8192.00
208 math500_math500_211 1.000 4 4 8192.00
209 math500_math500_212 1.000 4 4 8192.00
210 math500_math500_208 1.000 4 4 8192.00
211 math500_math500_205 0.500 2 4 8192.00
212 math500_math500_215 1.000 4 4 8192.00
213 math500_math500_204 0.000 0 4 8192.00
214 math500_math500_216 1.000 4 4 8192.00
215 math500_math500_213 0.750 3 4 8192.00
216 math500_math500_218 1.000 4 4 8192.00
217 math500_math500_202 0.750 3 4 8192.00
218 math500_math500_214 0.000 0 4 8192.00
219 math500_math500_220 1.000 4 4 8192.00
220 math500_math500_225 1.000 4 4 8192.00
221 math500_math500_217 0.000 0 4 8192.00
222 math500_math500_210 1.000 4 4 8192.00
223 math500_math500_223 0.000 0 4 8192.00
224 math500_math500_227 1.000 4 4 8192.00
225 math500_math500_229 1.000 4 4 8192.00
226 math500_math500_231 1.000 4 4 8192.00
227 math500_math500_221 1.000 4 4 8192.00
228 math500_math500_235 0.750 3 4 8192.00
229 math500_math500_219 0.250 1 4 8191.75
230 math500_math500_226 1.000 4 4 8192.00
231 math500_math500_224 0.000 0 4 8192.00
232 math500_math500_228 0.500 2 4 8192.00
233 math500_math500_233 1.000 4 4 8192.00
234 math500_math500_237 1.000 4 4 8192.00
235 math500_math500_222 0.250 1 4 8192.00
236 math500_math500_234 1.000 4 4 8192.00
237 math500_math500_243 1.000 4 4 8192.00
238 math500_math500_238 1.000 4 4 8192.00
239 math500_math500_241 1.000 4 4 8192.00
240 math500_math500_230 1.000 4 4 8192.00
241 math500_math500_236 0.500 2 4 8192.00
242 math500_math500_247 1.000 4 4 8192.00
243 math500_math500_232 0.000 0 4 8192.00
244 math500_math500_239 0.000 0 4 8191.75
245 math500_math500_253 1.000 4 4 8192.00
246 math500_math500_250 1.000 4 4 8192.00
247 math500_math500_245 0.250 1 4 8192.00
248 math500_math500_242 0.000 0 4 8192.00
249 math500_math500_244 1.000 4 4 8192.00
250 math500_math500_257 1.000 4 4 8192.00
251 math500_math500_259 0.750 3 4 8192.00
252 math500_math500_240 0.000 0 4 8192.00
253 math500_math500_246 0.500 2 4 8192.00
254 math500_math500_251 1.000 4 4 8192.00
255 math500_math500_255 1.000 4 4 8192.00
256 math500_math500_252 1.000 4 4 8192.00
257 math500_math500_249 0.500 2 4 8192.00
258 math500_math500_258 1.000 4 4 8192.00
259 math500_math500_256 1.000 4 4 8192.00
260 math500_math500_248 0.000 0 4 8193.00
261 math500_math500_263 1.000 4 4 8192.00
262 math500_math500_261 0.750 3 4 8192.00
263 math500_math500_260 1.000 4 4 8192.00
264 math500_math500_254 0.750 3 4 8192.00
265 math500_math500_265 1.000 4 4 8192.00
266 math500_math500_262 1.000 4 4 8192.00
267 math500_math500_269 0.750 3 4 8192.00
268 math500_math500_270 1.000 4 4 8192.00
269 math500_math500_266 1.000 4 4 8192.00
270 math500_math500_271 1.000 4 4 8192.00
271 math500_math500_268 1.000 4 4 8192.00
272 math500_math500_275 1.000 4 4 8192.00
273 math500_math500_273 1.000 4 4 8192.00
274 math500_math500_277 1.000 4 4 8192.00
275 math500_math500_272 0.750 3 4 8192.00
276 math500_math500_278 1.000 4 4 8192.00
277 math500_math500_283 1.000 4 4 8192.00
278 math500_math500_267 0.000 0 4 8191.75
279 math500_math500_280 1.000 4 4 8192.00
280 math500_math500_279 0.250 1 4 8192.00
281 math500_math500_264 0.000 0 4 8192.00
282 math500_math500_276 1.000 4 4 8192.00
283 math500_math500_287 0.750 3 4 8192.00
284 math500_math500_290 1.000 4 4 8192.00
285 math500_math500_285 0.250 1 4 8192.00
286 math500_math500_274 0.000 0 4 8192.00
287 math500_math500_282 0.500 2 4 8192.00
288 math500_math500_293 1.000 4 4 8192.00
289 math500_math500_281 0.000 0 4 8192.00
290 math500_math500_284 0.250 1 4 8192.00
291 math500_math500_289 0.750 3 4 8192.00
292 math500_math500_286 0.000 0 4 8192.00
293 math500_math500_292 0.500 2 4 8192.00
294 math500_math500_297 1.000 4 4 8192.00
295 math500_math500_298 0.750 3 4 8192.00
296 math500_math500_291 0.750 3 4 8192.00
297 math500_math500_288 0.250 1 4 8192.00
298 math500_math500_294 0.750 3 4 8192.00
299 math500_math500_295 0.000 0 4 8192.00
300 math500_math500_299 1.000 4 4 8192.00
301 math500_math500_304 1.000 4 4 8192.00
302 math500_math500_305 1.000 4 4 8192.00
303 math500_math500_300 1.000 4 4 8192.00
304 math500_math500_296 0.250 1 4 8192.00
305 math500_math500_302 0.250 1 4 8192.00
306 math500_math500_307 0.250 1 4 8192.00
307 math500_math500_301 0.750 3 4 8192.00
308 math500_math500_309 0.000 0 4 8192.00
309 math500_math500_303 0.500 2 4 8192.00
310 math500_math500_312 1.000 4 4 8192.00
311 math500_math500_310 1.000 4 4 8192.00
312 math500_math500_313 1.000 4 4 8192.00
313 math500_math500_314 1.000 4 4 8192.00
314 math500_math500_319 1.000 4 4 8192.00
315 math500_math500_311 0.750 3 4 8192.00
316 math500_math500_315 1.000 4 4 8192.00
317 math500_math500_316 1.000 4 4 8192.00
318 math500_math500_321 1.000 4 4 8192.00
319 math500_math500_306 0.000 0 4 8192.00
320 math500_math500_322 1.000 4 4 8192.00
321 math500_math500_325 1.000 4 4 8192.00
322 math500_math500_308 0.000 0 4 8192.00
323 math500_math500_318 1.000 4 4 8192.00
324 math500_math500_317 0.750 3 4 8192.00
325 math500_math500_329 1.000 4 4 8192.00
326 math500_math500_332 0.750 3 4 8192.00
327 math500_math500_320 0.250 1 4 8192.00
328 math500_math500_330 1.000 4 4 8192.00
329 math500_math500_331 1.000 4 4 8192.00
330 math500_math500_327 0.000 0 4 8192.00
331 math500_math500_335 0.750 3 4 8192.00
332 math500_math500_336 1.000 4 4 8192.00
333 math500_math500_326 1.000 4 4 8192.00
334 math500_math500_334 0.750 3 4 8192.00
335 math500_math500_324 0.000 0 4 8192.00
336 math500_math500_328 0.250 1 4 8192.50
337 math500_math500_338 1.000 4 4 8192.00
338 math500_math500_323 0.250 1 4 8192.00
339 math500_math500_333 0.250 1 4 8192.00
340 math500_math500_337 1.000 4 4 8192.00
341 math500_math500_345 0.750 3 4 8192.00
342 math500_math500_343 1.000 4 4 8192.00
343 math500_math500_341 1.000 4 4 8192.00
344 math500_math500_344 1.000 4 4 8192.00
345 math500_math500_339 1.000 4 4 8192.00
346 math500_math500_342 1.000 4 4 8192.00
347 math500_math500_347 1.000 4 4 8192.00
348 math500_math500_353 1.000 4 4 8192.00
349 math500_math500_340 0.000 0 4 8192.00
350 math500_math500_350 1.000 4 4 8192.00
351 math500_math500_348 0.750 3 4 8192.00
352 math500_math500_354 1.000 4 4 8192.00
353 math500_math500_346 0.750 3 4 8192.00
354 math500_math500_351 0.250 1 4 8192.00
355 math500_math500_356 1.000 4 4 8192.00
356 math500_math500_358 0.500 2 4 8192.00
357 math500_math500_363 1.000 4 4 8192.00
358 math500_math500_359 0.500 2 4 8191.75
359 math500_math500_352 0.000 0 4 8192.00
360 math500_math500_357 1.000 4 4 8191.75
361 math500_math500_367 1.000 4 4 8192.00
362 math500_math500_355 0.000 0 4 8192.00
363 math500_math500_364 0.750 3 4 8192.00
364 math500_math500_360 1.000 4 4 8192.00
365 math500_math500_362 1.000 4 4 8192.00
366 math500_math500_370 1.000 4 4 8192.00
367 math500_math500_349 0.250 1 4 8192.00
368 math500_math500_368 1.000 4 4 8192.00
369 math500_math500_361 0.000 0 4 8192.00
370 math500_math500_366 1.000 4 4 8192.00
371 math500_math500_374 1.000 4 4 8192.00
372 math500_math500_376 1.000 4 4 8192.00
373 math500_math500_373 1.000 4 4 8192.00
374 math500_math500_378 1.000 4 4 8192.00
375 math500_math500_365 0.250 1 4 8192.00
376 math500_math500_384 1.000 4 4 8192.00
377 math500_math500_369 0.000 0 4 8192.00
378 math500_math500_383 1.000 4 4 8192.00
379 math500_math500_375 1.000 4 4 8192.00
380 math500_math500_372 0.500 2 4 8191.25
381 math500_math500_371 0.000 0 4 8192.00
382 math500_math500_380 0.250 1 4 8192.00
383 math500_math500_379 1.000 4 4 8192.00
384 math500_math500_388 1.000 4 4 8192.00
385 math500_math500_386 1.000 4 4 8192.00
386 math500_math500_387 1.000 4 4 8192.00
387 math500_math500_382 0.500 2 4 8192.00
388 math500_math500_385 0.750 3 4 8192.00
389 math500_math500_377 0.500 2 4 8198.75
390 math500_math500_389 1.000 4 4 8192.00
391 math500_math500_393 1.000 4 4 8192.00
392 math500_math500_381 0.000 0 4 8192.00
393 math500_math500_397 1.000 4 4 8192.00
394 math500_math500_395 1.000 4 4 8192.00
395 math500_math500_390 0.500 2 4 8192.00
396 math500_math500_398 0.750 3 4 8192.00
397 math500_math500_392 0.000 0 4 8192.00
398 math500_math500_394 0.500 2 4 8192.00
399 math500_math500_391 1.000 4 4 8192.00
400 math500_math500_399 1.000 4 4 8192.00
401 math500_math500_402 0.500 2 4 8192.00
402 math500_math500_404 1.000 4 4 8192.00
403 math500_math500_406 1.000 4 4 8192.00
404 math500_math500_407 1.000 4 4 8192.00
405 math500_math500_405 1.000 4 4 8192.00
406 math500_math500_403 0.000 0 4 8192.00
407 math500_math500_410 1.000 4 4 8192.00
408 math500_math500_396 1.000 4 4 8192.00
409 math500_math500_400 0.000 0 4 8192.00
410 math500_math500_409 1.000 4 4 8192.00
411 math500_math500_411 1.000 4 4 8192.00
412 math500_math500_414 1.000 4 4 8193.00
413 math500_math500_413 1.000 4 4 8192.00
414 math500_math500_401 0.250 1 4 8191.75
415 math500_math500_415 1.000 4 4 8192.00
416 math500_math500_408 0.250 1 4 8192.00
417 math500_math500_417 1.000 4 4 8192.00
418 math500_math500_418 1.000 4 4 8192.00
419 math500_math500_420 1.000 4 4 8197.50
420 math500_math500_424 1.000 4 4 8192.00
421 math500_math500_427 1.000 4 4 8192.00
422 math500_math500_416 0.500 2 4 8192.00
423 math500_math500_412 0.000 0 4 8192.00
424 math500_math500_426 1.000 4 4 8192.00
425 math500_math500_421 0.000 0 4 8192.00
426 math500_math500_430 1.000 4 4 8192.00
427 math500_math500_429 1.000 4 4 8192.00
428 math500_math500_422 0.000 0 4 8191.25
429 math500_math500_423 1.000 4 4 8192.00
430 math500_math500_419 0.250 1 4 8192.00
431 math500_math500_431 1.000 4 4 8192.00
432 math500_math500_433 1.000 4 4 8192.00
433 math500_math500_428 1.000 4 4 8192.00
434 math500_math500_425 0.000 0 4 8192.00
435 math500_math500_435 1.000 4 4 8192.00
436 math500_math500_434 1.000 4 4 8192.00
437 math500_math500_440 1.000 4 4 8192.00
438 math500_math500_441 1.000 4 4 8192.00
439 math500_math500_432 0.000 0 4 8192.00
440 math500_math500_436 0.750 3 4 8192.00
441 math500_math500_443 1.000 4 4 8192.00
442 math500_math500_437 1.000 4 4 8192.00
443 math500_math500_442 1.000 4 4 8192.00
444 math500_math500_438 1.000 4 4 8192.00
445 math500_math500_439 0.500 2 4 8192.00
446 math500_math500_447 1.000 4 4 8192.00
447 math500_math500_446 0.750 3 4 8192.00
448 math500_math500_449 1.000 4 4 8192.00
449 math500_math500_448 1.000 4 4 8192.00
450 math500_math500_453 1.000 4 4 8192.00
451 math500_math500_455 1.000 4 4 8192.00
452 math500_math500_445 0.500 2 4 8192.00
453 math500_math500_452 1.000 4 4 8192.00
454 math500_math500_450 1.000 4 4 8192.00
455 math500_math500_456 0.750 3 4 8192.00
456 math500_math500_444 0.000 0 4 8192.00
457 math500_math500_454 0.750 3 4 8192.00
458 math500_math500_457 1.000 4 4 8192.00
459 math500_math500_451 1.000 4 4 8192.00
460 math500_math500_461 0.750 3 4 8192.00
461 math500_math500_463 1.000 4 4 8192.00
462 math500_math500_458 0.750 3 4 8192.00
463 math500_math500_465 1.000 4 4 8192.00
464 math500_math500_464 1.000 4 4 8192.00
465 math500_math500_471 1.000 4 4 8192.00
466 math500_math500_459 1.000 4 4 8192.00
467 math500_math500_468 1.000 4 4 8192.00
468 math500_math500_472 1.000 4 4 8192.00
469 math500_math500_469 1.000 4 4 8192.00
470 math500_math500_467 0.750 3 4 8192.00
471 math500_math500_460 0.000 0 4 8192.25
472 math500_math500_462 0.500 2 4 8191.00
473 math500_math500_474 0.750 3 4 8192.00
474 math500_math500_466 0.000 0 4 8192.00
475 math500_math500_476 1.000 4 4 8192.00
476 math500_math500_477 1.000 4 4 8192.00
477 math500_math500_473 0.750 3 4 8192.00
478 math500_math500_479 1.000 4 4 8192.00
479 math500_math500_483 1.000 4 4 8192.00
480 math500_math500_470 0.250 1 4 8190.50
481 math500_math500_487 1.000 4 4 8192.00
482 math500_math500_475 0.000 0 4 8192.00
483 math500_math500_485 0.500 2 4 8192.00
484 math500_math500_480 1.000 4 4 8192.00
485 math500_math500_488 1.000 4 4 8192.00
486 math500_math500_484 1.000 4 4 8192.00
487 math500_math500_478 0.000 0 4 8192.00
488 math500_math500_481 0.000 0 4 8192.00
489 math500_math500_482 0.500 2 4 8192.00
490 math500_math500_492 1.000 4 4 8192.00
491 math500_math500_490 0.250 1 4 8192.00
492 math500_math500_486 0.750 3 4 8192.00
493 math500_math500_493 0.750 3 4 8192.00
494 math500_math500_495 1.000 4 4 8192.00
495 math500_math500_496 1.000 4 4 8192.00
496 math500_math500_489 1.000 4 4 8192.00
497 math500_math500_499 0.750 3 4 8192.00
498 math500_math500_498 1.000 4 4 8192.00
499 math500_math500_491 0.250 1 4 8192.00
500 math500_math500_497 0.000 0 4 8192.00
501 math500_math500_494 0.000 0 4 8192.00
502 Total Accuracy 0.730 1460 2000 8191.93

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,12022305,73.37832641601562
2,1149492,7.0159423828125
3,634015,3.869720458984375
4,2578188,15.736010742187501
Total Tokens,16384000,100.0
1 iter_count token_count percentage
2 1 12022305 73.37832641601562
3 2 1149492 7.0159423828125
4 3 634015 3.869720458984375
5 4 2578188 15.736010742187501
6 Total Tokens 16384000 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@4": 0.856,
"cons@4": 0.8,
"avg@4": 0.73,
"avg_output_length": 8191.93,
"num_problems": 500,
"num_samples": 2000,
"repeat_size": 4,
"avg_request_time": 97.3714,
"end_2_end_time": 1583.5418,
"token_throughtput": 10346.3398,
"request_throught": 1.263,
"avg_iter_count": 1.6196,
"total_concurrency": 128,
"failed_requests": 0
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03fd25fabfbb60bc15d4d4b553c8fb52dd390d3cf5452fe26becbe86a49c7689
size 49228611

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 8192
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 4
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,678 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
olympiadbench_1750,0.000,0,4,8192.00
olympiadbench_1620,0.000,0,4,8192.00
olympiadbench_1697,0.000,0,4,8192.00
olympiadbench_1709,0.000,0,4,8191.75
olympiadbench_1618,0.000,0,4,8192.00
olympiadbench_1760,0.000,0,4,8192.00
olympiadbench_1644,0.000,0,4,8192.00
olympiadbench_1695,0.000,0,4,8192.00
olympiadbench_1645,0.000,0,4,8192.00
olympiadbench_1694,0.000,0,4,8192.00
olympiadbench_1678,0.000,0,4,8192.00
olympiadbench_1606,0.250,1,4,8192.00
olympiadbench_1687,0.000,0,4,8192.00
olympiadbench_1631,0.000,0,4,8192.00
olympiadbench_1718,0.000,0,4,8192.00
olympiadbench_1736,0.000,0,4,8192.00
olympiadbench_1747,0.000,0,4,8192.00
olympiadbench_1737,0.000,0,4,8192.00
olympiadbench_1659,0.250,1,4,8192.00
olympiadbench_1675,0.500,2,4,8192.00
olympiadbench_1681,0.250,1,4,8192.00
olympiadbench_1724,0.000,0,4,8192.00
olympiadbench_1613,0.250,1,4,8192.00
olympiadbench_1723,0.000,0,4,8192.00
olympiadbench_1612,0.000,0,4,8192.00
olympiadbench_1664,0.000,0,4,8192.00
olympiadbench_1716,0.000,0,4,8192.00
olympiadbench_1610,0.000,0,4,8192.00
olympiadbench_1641,0.000,0,4,8192.00
olympiadbench_1738,0.000,0,4,8192.00
olympiadbench_1662,0.000,0,4,8192.00
olympiadbench_1614,0.000,0,4,8192.00
olympiadbench_1766,0.000,0,4,8192.00
olympiadbench_1789,0.000,0,4,8192.00
olympiadbench_1818,0.000,0,4,8192.00
olympiadbench_1810,0.000,0,4,8192.00
olympiadbench_1866,0.250,1,4,8192.00
olympiadbench_1828,0.000,0,4,8192.00
olympiadbench_1807,0.000,0,4,8192.00
olympiadbench_1775,0.000,0,4,8192.00
olympiadbench_1798,0.250,1,4,8192.00
olympiadbench_1800,0.000,0,4,8192.00
olympiadbench_1820,0.000,0,4,8192.00
olympiadbench_1843,0.500,2,4,8192.00
olympiadbench_1833,0.000,0,4,8192.00
olympiadbench_1854,0.000,0,4,8191.75
olympiadbench_1832,0.000,0,4,8192.00
olympiadbench_1845,0.000,0,4,8192.00
olympiadbench_1869,0.000,0,4,8192.00
olympiadbench_1834,0.250,1,4,8192.00
olympiadbench_1782,0.000,0,4,8191.00
olympiadbench_1883,0.000,0,4,8192.00
olympiadbench_1872,0.000,0,4,8192.00
olympiadbench_1874,0.000,0,4,8192.00
olympiadbench_1879,0.000,0,4,8192.00
olympiadbench_1847,0.250,1,4,8192.00
olympiadbench_1915,0.000,0,4,8192.00
olympiadbench_1838,0.000,0,4,8192.00
olympiadbench_1887,0.000,0,4,8192.00
olympiadbench_1873,0.000,0,4,8191.50
olympiadbench_1918,0.000,0,4,8192.00
olympiadbench_1914,0.000,0,4,8192.00
olympiadbench_1882,0.000,0,4,8192.00
olympiadbench_1920,0.000,0,4,8192.00
olympiadbench_1929,0.250,1,4,8192.00
olympiadbench_1930,0.000,0,4,8192.00
olympiadbench_1938,0.000,0,4,8192.00
olympiadbench_1964,0.000,0,4,8192.00
olympiadbench_1965,0.000,0,4,8192.00
olympiadbench_1940,0.000,0,4,8192.00
olympiadbench_1962,0.000,0,4,8192.00
olympiadbench_1939,0.000,0,4,8192.00
olympiadbench_1969,0.000,0,4,8192.00
olympiadbench_1974,0.000,0,4,8192.00
olympiadbench_1945,0.000,0,4,8191.75
olympiadbench_1953,0.000,0,4,8192.00
olympiadbench_1988,0.000,0,4,8192.00
olympiadbench_2004,0.000,0,4,8179.75
olympiadbench_2000,0.000,0,4,8192.00
olympiadbench_1970,0.000,0,4,8192.00
olympiadbench_1968,0.250,1,4,8192.00
olympiadbench_1997,0.000,0,4,8192.00
olympiadbench_1977,0.000,0,4,8191.75
olympiadbench_2012,0.000,0,4,8192.00
olympiadbench_2006,0.000,0,4,8192.00
olympiadbench_2024,0.000,0,4,8192.00
olympiadbench_2010,0.000,0,4,8192.00
olympiadbench_1998,0.000,0,4,8192.00
olympiadbench_2022,0.250,1,4,8192.00
olympiadbench_2035,0.000,0,4,8192.00
olympiadbench_2021,0.000,0,4,8192.00
olympiadbench_2037,0.000,0,4,8192.00
olympiadbench_2011,0.000,0,4,8192.00
olympiadbench_2032,0.000,0,4,8192.00
olympiadbench_2029,0.750,3,4,8192.00
olympiadbench_2040,0.000,0,4,8192.00
olympiadbench_2099,0.000,0,4,8191.25
olympiadbench_2082,0.000,0,4,8192.00
olympiadbench_2084,0.000,0,4,8192.00
olympiadbench_2075,0.000,0,4,8192.00
olympiadbench_2111,0.000,0,4,8192.00
olympiadbench_2064,0.000,0,4,8192.00
olympiadbench_2095,0.000,0,4,8192.00
olympiadbench_2151,0.000,0,4,8192.00
olympiadbench_2063,0.000,0,4,8192.00
olympiadbench_2045,0.000,0,4,8192.00
olympiadbench_2177,0.500,2,4,8192.00
olympiadbench_2147,0.000,0,4,8192.00
olympiadbench_2165,0.000,0,4,8192.00
olympiadbench_2124,0.250,1,4,8192.00
olympiadbench_2126,0.000,0,4,8192.00
olympiadbench_2091,0.000,0,4,8192.00
olympiadbench_2153,0.000,0,4,8192.00
olympiadbench_2171,0.000,0,4,8192.00
olympiadbench_2152,0.000,0,4,8192.00
olympiadbench_2193,0.000,0,4,8192.00
olympiadbench_2127,0.000,0,4,8192.00
olympiadbench_2174,0.000,0,4,8192.00
olympiadbench_2198,0.000,0,4,8192.00
olympiadbench_2203,0.000,0,4,8192.00
olympiadbench_2235,1.000,4,4,8192.00
olympiadbench_2185,0.000,0,4,8192.00
olympiadbench_2204,0.000,0,4,8192.00
olympiadbench_2230,0.000,0,4,8192.00
olympiadbench_2236,1.000,4,4,8192.00
olympiadbench_2239,0.500,2,4,8191.75
olympiadbench_2212,0.000,0,4,8191.75
olympiadbench_2216,0.000,0,4,8192.00
olympiadbench_2248,1.000,4,4,8192.00
olympiadbench_2242,1.000,4,4,8192.00
olympiadbench_2234,1.000,4,4,8192.00
olympiadbench_2241,1.000,4,4,8192.00
olympiadbench_2238,1.000,4,4,8193.50
olympiadbench_2251,0.750,3,4,8192.00
olympiadbench_2247,1.000,4,4,8192.00
olympiadbench_2258,0.250,1,4,8192.00
olympiadbench_2243,1.000,4,4,8192.00
olympiadbench_2253,0.500,2,4,8192.00
olympiadbench_2261,0.500,2,4,8192.00
olympiadbench_2256,1.000,4,4,8192.00
olympiadbench_2249,1.000,4,4,8192.00
olympiadbench_2260,0.500,2,4,8192.00
olympiadbench_2265,0.500,2,4,8192.00
olympiadbench_2268,1.000,4,4,8192.00
olympiadbench_2257,0.750,3,4,8192.00
olympiadbench_2276,0.000,0,4,8192.00
olympiadbench_2254,0.000,0,4,8192.00
olympiadbench_2255,0.000,0,4,8192.00
olympiadbench_2266,1.000,4,4,8192.00
olympiadbench_2280,1.000,4,4,8192.00
olympiadbench_2288,0.250,1,4,8192.00
olympiadbench_2281,1.000,4,4,8192.00
olympiadbench_2277,1.000,4,4,8192.00
olympiadbench_2275,0.250,1,4,8192.00
olympiadbench_2263,1.000,4,4,8192.00
olympiadbench_2286,1.000,4,4,8192.00
olympiadbench_2282,0.750,3,4,8192.00
olympiadbench_2292,1.000,4,4,8192.00
olympiadbench_2287,0.500,2,4,8192.00
olympiadbench_2283,0.000,0,4,8192.00
olympiadbench_2289,1.000,4,4,8192.00
olympiadbench_2303,0.000,0,4,8192.00
olympiadbench_2300,1.000,4,4,8192.00
olympiadbench_2322,1.000,4,4,8192.00
olympiadbench_2312,1.000,4,4,8192.00
olympiadbench_2313,0.750,3,4,8192.00
olympiadbench_2325,0.000,0,4,8192.00
olympiadbench_2298,0.000,0,4,8192.00
olympiadbench_2327,0.750,3,4,8192.00
olympiadbench_2315,0.250,1,4,8192.00
olympiadbench_2317,1.000,4,4,8192.00
olympiadbench_2328,1.000,4,4,8192.00
olympiadbench_2301,0.000,0,4,8192.00
olympiadbench_2323,0.750,3,4,8192.00
olympiadbench_2329,1.000,4,4,8192.00
olympiadbench_2321,1.000,4,4,8192.00
olympiadbench_2319,0.000,0,4,8192.00
olympiadbench_2331,1.000,4,4,8192.00
olympiadbench_2326,1.000,4,4,8192.00
olympiadbench_2332,0.750,3,4,8192.00
olympiadbench_2318,0.000,0,4,8192.00
olympiadbench_2339,1.000,4,4,8192.00
olympiadbench_2343,1.000,4,4,8192.00
olympiadbench_2334,0.250,1,4,8192.00
olympiadbench_2330,0.250,1,4,8192.00
olympiadbench_2336,0.000,0,4,8192.00
olympiadbench_2345,1.000,4,4,8192.00
olympiadbench_2338,1.000,4,4,8192.00
olympiadbench_2333,0.000,0,4,8190.50
olympiadbench_2351,1.000,4,4,8192.00
olympiadbench_2340,0.750,3,4,8192.00
olympiadbench_2344,0.750,3,4,8192.00
olympiadbench_2352,1.000,4,4,8192.00
olympiadbench_2342,1.000,4,4,8192.00
olympiadbench_2341,0.000,0,4,8192.00
olympiadbench_2346,1.000,4,4,8192.00
olympiadbench_2349,0.000,0,4,8192.00
olympiadbench_2371,1.000,4,4,8192.00
olympiadbench_2359,1.000,4,4,8192.00
olympiadbench_2369,1.000,4,4,8192.00
olympiadbench_2356,0.000,0,4,8192.00
olympiadbench_2355,0.500,2,4,8192.00
olympiadbench_2361,0.250,1,4,8192.00
olympiadbench_2376,1.000,4,4,8192.00
olympiadbench_2350,0.000,0,4,8192.00
olympiadbench_2375,0.500,2,4,8192.00
olympiadbench_2388,1.000,4,4,8192.00
olympiadbench_2370,0.750,3,4,8192.50
olympiadbench_2372,1.000,4,4,8192.00
olympiadbench_2391,1.000,4,4,8192.00
olympiadbench_2403,1.000,4,4,8192.00
olympiadbench_2380,0.000,0,4,8191.25
olympiadbench_2390,1.000,4,4,8192.00
olympiadbench_2392,0.750,3,4,8192.00
olympiadbench_2397,1.000,4,4,8192.00
olympiadbench_2382,0.500,2,4,8192.00
olympiadbench_2377,0.000,0,4,8192.00
olympiadbench_2409,0.500,2,4,8192.00
olympiadbench_2410,1.000,4,4,8192.00
olympiadbench_2420,1.000,4,4,8192.00
olympiadbench_2384,0.000,0,4,8192.00
olympiadbench_2419,1.000,4,4,8192.00
olympiadbench_2407,0.000,0,4,8192.00
olympiadbench_2421,1.000,4,4,8192.00
olympiadbench_2408,0.250,1,4,8192.00
olympiadbench_2414,0.500,2,4,8192.00
olympiadbench_2425,1.000,4,4,8192.00
olympiadbench_2415,0.000,0,4,8192.00
olympiadbench_2423,0.500,2,4,8191.75
olympiadbench_2431,1.000,4,4,8192.00
olympiadbench_2426,0.250,1,4,8192.00
olympiadbench_2438,1.000,4,4,8192.00
olympiadbench_2435,0.500,2,4,8192.00
olympiadbench_2427,0.750,3,4,8192.00
olympiadbench_2422,0.750,3,4,8192.00
olympiadbench_2439,1.000,4,4,8192.00
olympiadbench_2432,0.250,1,4,8192.00
olympiadbench_2445,1.000,4,4,8192.50
olympiadbench_2444,1.000,4,4,8192.00
olympiadbench_2443,1.000,4,4,8192.00
olympiadbench_2441,0.500,2,4,8192.00
olympiadbench_2430,0.250,1,4,8192.00
olympiadbench_2458,1.000,4,4,8192.00
olympiadbench_2459,1.000,4,4,8192.00
olympiadbench_2442,0.000,0,4,8191.50
olympiadbench_2466,1.000,4,4,8192.00
olympiadbench_2454,1.000,4,4,8192.00
olympiadbench_2440,0.500,2,4,8192.00
olympiadbench_2453,0.000,0,4,8186.00
olympiadbench_2469,0.750,3,4,8191.75
olympiadbench_2460,0.500,2,4,8192.00
olympiadbench_2467,0.000,0,4,8192.00
olympiadbench_2461,0.000,0,4,8192.00
olympiadbench_2482,0.500,2,4,8192.00
olympiadbench_2479,1.000,4,4,8192.00
olympiadbench_2481,0.750,3,4,8192.00
olympiadbench_2463,0.000,0,4,8192.00
olympiadbench_2464,0.000,0,4,8192.00
olympiadbench_2472,0.000,0,4,8192.00
olympiadbench_2475,0.000,0,4,8192.00
olympiadbench_2492,1.000,4,4,8192.00
olympiadbench_2498,0.000,0,4,8192.00
olympiadbench_2494,1.000,4,4,8191.75
olympiadbench_2500,1.000,4,4,8192.00
olympiadbench_2489,0.000,0,4,8192.00
olympiadbench_2486,0.000,0,4,8192.00
olympiadbench_2496,0.750,3,4,8192.00
olympiadbench_2506,0.750,3,4,8192.00
olympiadbench_2508,1.000,4,4,8192.00
olympiadbench_2509,0.750,3,4,8192.00
olympiadbench_2501,0.000,0,4,8192.00
olympiadbench_2493,0.250,1,4,8192.00
olympiadbench_2504,1.000,4,4,8192.00
olympiadbench_2490,0.000,0,4,8192.00
olympiadbench_2502,0.500,2,4,8192.00
olympiadbench_2520,1.000,4,4,8192.00
olympiadbench_2510,0.750,3,4,8192.00
olympiadbench_2507,0.000,0,4,8189.75
olympiadbench_2531,1.000,4,4,8192.00
olympiadbench_2523,0.500,2,4,8191.75
olympiadbench_2532,0.750,3,4,8192.00
olympiadbench_2521,0.500,2,4,8192.00
olympiadbench_2536,1.000,4,4,8193.00
olympiadbench_2524,0.500,2,4,8192.00
olympiadbench_2548,1.000,4,4,8192.00
olympiadbench_2539,0.250,1,4,8192.00
olympiadbench_2527,0.500,2,4,8192.00
olympiadbench_2545,0.500,2,4,8192.00
olympiadbench_2522,0.000,0,4,8192.00
olympiadbench_2552,1.000,4,4,8192.00
olympiadbench_2544,0.000,0,4,8192.00
olympiadbench_2534,0.500,2,4,8192.00
olympiadbench_2549,0.000,0,4,8192.00
olympiadbench_2551,0.250,1,4,8192.00
olympiadbench_2525,0.000,0,4,8189.75
olympiadbench_2553,1.000,4,4,8192.00
olympiadbench_2560,0.500,2,4,8192.00
olympiadbench_2558,0.250,1,4,8192.00
olympiadbench_2568,1.000,4,4,8192.50
olympiadbench_2575,0.500,2,4,8192.00
olympiadbench_2578,1.000,4,4,8192.00
olympiadbench_2555,0.000,0,4,8192.00
olympiadbench_2565,0.000,0,4,8192.00
olympiadbench_2570,1.000,4,4,8192.00
olympiadbench_2569,0.750,3,4,8192.00
olympiadbench_2571,0.750,3,4,8192.00
olympiadbench_2559,0.750,3,4,8192.00
olympiadbench_2574,0.000,0,4,8192.00
olympiadbench_2577,0.500,2,4,8192.00
olympiadbench_2576,0.250,1,4,8192.00
olympiadbench_2572,0.250,1,4,8192.00
olympiadbench_2596,1.000,4,4,8192.00
olympiadbench_2584,0.000,0,4,8192.00
olympiadbench_2588,0.000,0,4,8192.00
olympiadbench_2580,0.500,2,4,8192.00
olympiadbench_2582,0.250,1,4,8192.00
olympiadbench_2583,0.500,2,4,8191.75
olympiadbench_2592,0.500,2,4,8192.00
olympiadbench_2598,0.750,3,4,8192.00
olympiadbench_2599,0.750,3,4,8192.00
olympiadbench_2606,0.000,0,4,8192.00
olympiadbench_2601,0.500,2,4,8192.00
olympiadbench_2603,0.000,0,4,8192.00
olympiadbench_2609,1.000,4,4,8192.00
olympiadbench_2604,0.000,0,4,8192.00
olympiadbench_2602,0.000,0,4,8191.75
olympiadbench_2608,0.500,2,4,8192.00
olympiadbench_2607,0.000,0,4,8192.00
olympiadbench_2626,0.000,0,4,8191.50
olympiadbench_2610,0.000,0,4,8192.00
olympiadbench_2600,0.000,0,4,8187.75
olympiadbench_2613,0.500,2,4,8192.00
olympiadbench_2637,1.000,4,4,8191.75
olympiadbench_2615,0.500,2,4,8192.00
olympiadbench_2635,0.000,0,4,8192.00
olympiadbench_2614,0.500,2,4,8192.00
olympiadbench_2612,0.000,0,4,8192.00
olympiadbench_2611,0.000,0,4,8192.00
olympiadbench_2636,1.000,4,4,8192.00
olympiadbench_2642,0.250,1,4,8192.00
olympiadbench_2625,0.000,0,4,8192.00
olympiadbench_2641,0.500,2,4,8192.00
olympiadbench_2650,1.000,4,4,8192.00
olympiadbench_2639,0.000,0,4,8192.00
olympiadbench_2647,0.000,0,4,8192.00
olympiadbench_2638,0.250,1,4,8192.00
olympiadbench_2648,1.000,4,4,8192.00
olympiadbench_2645,0.000,0,4,8192.00
olympiadbench_2644,0.250,1,4,8192.00
olympiadbench_2640,0.000,0,4,8192.00
olympiadbench_2652,1.000,4,4,8192.00
olympiadbench_2646,0.000,0,4,8192.00
olympiadbench_2653,1.000,4,4,8192.00
olympiadbench_2651,1.000,4,4,8192.00
olympiadbench_2657,1.000,4,4,8192.00
olympiadbench_2643,0.000,0,4,8192.00
olympiadbench_2649,0.500,2,4,8192.00
olympiadbench_2656,1.000,4,4,8192.00
olympiadbench_2658,1.000,4,4,8192.00
olympiadbench_2659,0.500,2,4,8192.00
olympiadbench_2661,1.000,4,4,8192.00
olympiadbench_2655,0.000,0,4,8192.00
olympiadbench_2662,1.000,4,4,8192.00
olympiadbench_2663,0.000,0,4,8192.00
olympiadbench_2654,0.000,0,4,8192.00
olympiadbench_2660,0.500,2,4,8192.00
olympiadbench_2666,0.000,0,4,8192.00
olympiadbench_2675,0.000,0,4,8192.00
olympiadbench_2667,0.250,1,4,8192.00
olympiadbench_2664,0.000,0,4,8192.00
olympiadbench_2665,0.000,0,4,8193.50
olympiadbench_2669,1.000,4,4,8192.00
olympiadbench_2670,0.000,0,4,8192.00
olympiadbench_2673,0.000,0,4,8192.00
olympiadbench_2684,0.250,1,4,8192.00
olympiadbench_2668,0.000,0,4,8192.00
olympiadbench_2671,0.500,2,4,8192.00
olympiadbench_2674,0.750,3,4,8192.00
olympiadbench_2678,0.500,2,4,8192.00
olympiadbench_2679,0.500,2,4,8192.00
olympiadbench_2687,0.000,0,4,8192.00
olympiadbench_2702,0.250,1,4,8192.00
olympiadbench_2676,0.000,0,4,8192.00
olympiadbench_2701,0.750,3,4,8192.00
olympiadbench_2677,0.000,0,4,8192.00
olympiadbench_2672,0.000,0,4,8192.00
olympiadbench_2707,0.750,3,4,8191.75
olympiadbench_2680,0.500,2,4,8191.50
olympiadbench_2705,0.000,0,4,8192.00
olympiadbench_2708,1.000,4,4,8192.00
olympiadbench_2711,0.000,0,4,8192.00
olympiadbench_2713,0.000,0,4,8192.00
olympiadbench_2709,0.000,0,4,8192.00
olympiadbench_2706,0.000,0,4,8192.00
olympiadbench_2710,0.500,2,4,8192.00
olympiadbench_2712,0.000,0,4,8192.00
olympiadbench_2714,0.000,0,4,8192.00
olympiadbench_2720,0.750,3,4,8192.00
olympiadbench_2718,1.000,4,4,8192.00
olympiadbench_2723,0.000,0,4,8192.00
olympiadbench_2715,0.000,0,4,8192.00
olympiadbench_2717,0.000,0,4,8192.00
olympiadbench_2735,0.000,0,4,8192.00
olympiadbench_2721,0.000,0,4,8192.00
olympiadbench_2732,0.750,3,4,8192.00
olympiadbench_2727,0.000,0,4,8192.00
olympiadbench_2728,0.250,1,4,8192.00
olympiadbench_2722,0.000,0,4,8192.00
olympiadbench_2731,0.000,0,4,8192.00
olympiadbench_2733,0.000,0,4,8192.00
olympiadbench_2725,0.000,0,4,8191.75
olympiadbench_2724,0.000,0,4,8192.00
olympiadbench_2730,0.000,0,4,8192.00
olympiadbench_2729,0.000,0,4,8192.00
olympiadbench_2726,0.250,1,4,8192.00
olympiadbench_2739,0.000,0,4,8192.00
olympiadbench_2736,0.000,0,4,8192.00
olympiadbench_2738,0.500,2,4,8192.00
olympiadbench_2737,0.000,0,4,8192.00
olympiadbench_2747,1.000,4,4,8192.00
olympiadbench_2741,0.000,0,4,8180.25
olympiadbench_2742,0.000,0,4,8192.00
olympiadbench_2740,0.000,0,4,8192.00
olympiadbench_2746,0.750,3,4,8192.00
olympiadbench_2748,1.000,4,4,8192.00
olympiadbench_2734,0.000,0,4,8192.00
olympiadbench_2744,0.250,1,4,8192.00
olympiadbench_2753,0.000,0,4,8192.00
olympiadbench_2745,0.000,0,4,8192.00
olympiadbench_2754,0.000,0,4,8192.00
olympiadbench_2763,0.000,0,4,8192.00
olympiadbench_2759,0.000,0,4,8192.00
olympiadbench_2764,0.000,0,4,8192.00
olympiadbench_2773,1.000,4,4,8192.00
olympiadbench_2760,0.250,1,4,8192.00
olympiadbench_2765,0.000,0,4,8192.00
olympiadbench_2761,0.750,3,4,8192.00
olympiadbench_2777,1.000,4,4,8192.50
olympiadbench_2762,0.000,0,4,8192.00
olympiadbench_2776,1.000,4,4,8192.00
olympiadbench_2767,0.000,0,4,8192.00
olympiadbench_2775,0.500,2,4,8191.25
olympiadbench_2770,0.000,0,4,8192.00
olympiadbench_2780,1.000,4,4,8192.00
olympiadbench_2766,0.000,0,4,8192.00
olympiadbench_2768,0.000,0,4,8192.00
olympiadbench_2772,0.750,3,4,8192.00
olympiadbench_2783,1.000,4,4,8192.00
olympiadbench_2771,0.000,0,4,8192.00
olympiadbench_2781,1.000,4,4,8192.00
olympiadbench_2778,1.000,4,4,8192.00
olympiadbench_2782,0.750,3,4,8192.00
olympiadbench_2787,0.750,3,4,8191.25
olympiadbench_2785,1.000,4,4,8192.00
olympiadbench_2784,0.500,2,4,8192.00
olympiadbench_2788,0.000,0,4,8192.00
olympiadbench_2786,0.750,3,4,8192.00
olympiadbench_2790,0.500,2,4,8192.00
olympiadbench_2789,0.000,0,4,8192.00
olympiadbench_2791,0.750,3,4,8192.00
olympiadbench_2792,0.000,0,4,8192.00
olympiadbench_2799,1.000,4,4,8192.00
olympiadbench_2793,0.000,0,4,8192.00
olympiadbench_2795,0.000,0,4,8192.00
olympiadbench_2827,0.000,0,4,8192.00
olympiadbench_2798,0.750,3,4,8189.25
olympiadbench_2823,1.000,4,4,8192.00
olympiadbench_2830,1.000,4,4,8192.00
olympiadbench_2800,0.000,0,4,8192.00
olympiadbench_2796,0.000,0,4,8192.00
olympiadbench_2794,0.000,0,4,8192.25
olympiadbench_2797,0.750,3,4,8191.75
olympiadbench_2831,1.000,4,4,8192.00
olympiadbench_2829,0.000,0,4,8192.00
olympiadbench_2802,0.250,1,4,8192.00
olympiadbench_2801,0.000,0,4,8192.00
olympiadbench_2817,0.250,1,4,8192.00
olympiadbench_2824,0.000,0,4,8192.00
olympiadbench_2821,0.000,0,4,8192.00
olympiadbench_2819,0.000,0,4,8192.00
olympiadbench_2818,1.000,4,4,8192.00
olympiadbench_2834,1.000,4,4,8192.00
olympiadbench_2822,0.000,0,4,8191.75
olympiadbench_2828,0.500,2,4,8192.00
olympiadbench_2836,1.000,4,4,8192.00
olympiadbench_2825,0.000,0,4,8192.50
olympiadbench_2839,0.250,1,4,8192.00
olympiadbench_2840,0.500,2,4,8192.00
olympiadbench_2842,1.000,4,4,8191.75
olympiadbench_2838,1.000,4,4,8192.00
olympiadbench_2841,0.500,2,4,8192.00
olympiadbench_2832,0.000,0,4,8192.00
olympiadbench_2835,0.750,3,4,8192.00
olympiadbench_2843,0.000,0,4,8192.00
olympiadbench_2845,0.500,2,4,8192.00
olympiadbench_2852,0.000,0,4,8192.00
olympiadbench_2846,0.250,1,4,8192.00
olympiadbench_2847,0.500,2,4,8192.00
olympiadbench_2849,0.750,3,4,8192.00
olympiadbench_2844,0.250,1,4,8191.75
olympiadbench_2848,0.750,3,4,8188.75
olympiadbench_2860,0.250,1,4,8192.00
olympiadbench_2850,0.000,0,4,8192.00
olympiadbench_2856,0.000,0,4,8192.00
olympiadbench_2853,0.750,3,4,8192.00
olympiadbench_2857,0.000,0,4,8192.00
olympiadbench_2854,0.000,0,4,8192.00
olympiadbench_2851,0.000,0,4,8192.00
olympiadbench_2858,0.500,2,4,8192.00
olympiadbench_2863,0.000,0,4,8192.00
olympiadbench_2855,0.000,0,4,8192.00
olympiadbench_2859,0.000,0,4,8192.00
olympiadbench_2861,0.000,0,4,8192.00
olympiadbench_2887,0.000,0,4,8192.00
olympiadbench_2890,0.500,2,4,8192.00
olympiadbench_2862,0.000,0,4,8192.00
olympiadbench_2898,1.000,4,4,8192.00
olympiadbench_2891,0.000,0,4,8192.00
olympiadbench_2888,0.000,0,4,8192.00
olympiadbench_2901,1.000,4,4,8192.00
olympiadbench_2892,0.000,0,4,8192.00
olympiadbench_2884,0.250,1,4,8191.75
olympiadbench_2903,0.750,3,4,8192.00
olympiadbench_2894,0.000,0,4,8192.00
olympiadbench_2893,0.000,0,4,8192.00
olympiadbench_2905,1.000,4,4,8192.00
olympiadbench_2895,0.000,0,4,8192.00
olympiadbench_2900,1.000,4,4,8192.00
olympiadbench_2896,0.000,0,4,8192.00
olympiadbench_2909,1.000,4,4,8192.00
olympiadbench_2904,1.000,4,4,8192.00
olympiadbench_2902,0.750,3,4,8192.00
olympiadbench_2899,0.750,3,4,8192.00
olympiadbench_2907,1.000,4,4,8192.00
olympiadbench_2911,1.000,4,4,8192.00
olympiadbench_2908,1.000,4,4,8192.00
olympiadbench_2897,0.000,0,4,8187.50
olympiadbench_2912,0.250,1,4,8192.00
olympiadbench_2910,0.500,2,4,8192.00
olympiadbench_2913,0.500,2,4,8192.00
olympiadbench_2914,0.000,0,4,8192.00
olympiadbench_2922,1.000,4,4,8192.00
olympiadbench_2920,0.000,0,4,8191.75
olympiadbench_2916,0.000,0,4,8192.00
olympiadbench_2918,0.500,2,4,8192.00
olympiadbench_2947,0.250,1,4,8191.25
olympiadbench_2915,0.250,1,4,8192.00
olympiadbench_2919,0.000,0,4,8187.25
olympiadbench_2917,0.000,0,4,8192.00
olympiadbench_2925,1.000,4,4,8192.00
olympiadbench_2951,0.000,0,4,8192.00
olympiadbench_2924,0.500,2,4,8192.00
olympiadbench_2927,1.000,4,4,8192.00
olympiadbench_2953,0.000,0,4,8192.00
olympiadbench_2921,0.000,0,4,8192.00
olympiadbench_2949,0.000,0,4,8192.00
olympiadbench_2926,1.000,4,4,8192.00
olympiadbench_2950,0.500,2,4,8191.50
olympiadbench_2948,0.250,1,4,8192.00
olympiadbench_2955,0.250,1,4,8191.50
olympiadbench_2963,1.000,4,4,8192.00
olympiadbench_2957,0.000,0,4,8192.00
olympiadbench_2952,0.000,0,4,8192.00
olympiadbench_2960,1.000,4,4,8192.00
olympiadbench_2954,0.000,0,4,8192.00
olympiadbench_2971,0.000,0,4,8192.00
olympiadbench_2958,0.000,0,4,8192.00
olympiadbench_2956,0.000,0,4,8192.00
olympiadbench_2966,0.750,3,4,8192.00
olympiadbench_2961,0.750,3,4,8192.00
olympiadbench_2972,1.000,4,4,8192.00
olympiadbench_2968,1.000,4,4,8192.00
olympiadbench_2962,0.250,1,4,8192.00
olympiadbench_2964,0.500,2,4,8192.00
olympiadbench_2970,1.000,4,4,8192.00
olympiadbench_2974,0.500,2,4,8192.00
olympiadbench_2967,0.000,0,4,8192.00
olympiadbench_2969,0.000,0,4,8192.00
olympiadbench_2985,0.750,3,4,8192.00
olympiadbench_2977,1.000,4,4,8192.00
olympiadbench_2975,0.250,1,4,8187.50
olympiadbench_2978,0.000,0,4,8192.00
olympiadbench_2973,0.000,0,4,8192.00
olympiadbench_2979,0.250,1,4,8192.00
olympiadbench_2986,0.750,3,4,8192.00
olympiadbench_2976,0.500,2,4,8192.00
olympiadbench_2984,0.000,0,4,8192.00
olympiadbench_2980,0.000,0,4,8192.00
olympiadbench_2983,0.000,0,4,8192.00
olympiadbench_2981,0.000,0,4,8192.00
olympiadbench_2982,0.000,0,4,8192.00
olympiadbench_2988,0.250,1,4,8192.00
olympiadbench_2987,0.000,0,4,8192.00
olympiadbench_2990,0.000,0,4,8192.00
olympiadbench_2989,1.000,4,4,8192.00
olympiadbench_3008,0.000,0,4,8192.00
olympiadbench_2994,0.000,0,4,8192.00
olympiadbench_2992,0.000,0,4,8192.00
olympiadbench_2991,0.750,3,4,8192.00
olympiadbench_2996,0.500,2,4,8192.00
olympiadbench_3011,0.000,0,4,8192.00
olympiadbench_3021,0.750,3,4,8192.00
olympiadbench_3013,0.500,2,4,8192.00
olympiadbench_2993,0.250,1,4,8192.00
olympiadbench_3015,0.000,0,4,8192.00
olympiadbench_2995,0.500,2,4,8192.00
olympiadbench_3006,0.000,0,4,8187.50
olympiadbench_3001,0.000,0,4,8192.00
olympiadbench_3000,0.000,0,4,8191.75
olympiadbench_3004,0.750,3,4,8192.00
olympiadbench_3007,0.000,0,4,8192.00
olympiadbench_3010,0.000,0,4,8192.00
olympiadbench_3019,1.000,4,4,8192.00
olympiadbench_3018,0.000,0,4,8192.00
olympiadbench_3012,0.000,0,4,8192.00
olympiadbench_3022,0.750,3,4,8192.00
olympiadbench_3016,0.000,0,4,8192.00
olympiadbench_3014,0.000,0,4,8192.00
olympiadbench_3024,1.000,4,4,8192.00
olympiadbench_3009,0.500,2,4,8192.00
olympiadbench_3020,0.500,2,4,8192.00
olympiadbench_3017,0.000,0,4,8192.00
olympiadbench_3028,1.000,4,4,8192.00
olympiadbench_3027,1.000,4,4,8192.00
olympiadbench_3030,1.000,4,4,8192.00
olympiadbench_3037,0.000,0,4,8192.00
olympiadbench_3033,1.000,4,4,8192.00
olympiadbench_3025,0.750,3,4,8192.00
olympiadbench_3031,1.000,4,4,8192.00
olympiadbench_3026,0.500,2,4,8191.50
olympiadbench_3023,0.250,1,4,8192.00
olympiadbench_3032,1.000,4,4,8192.00
olympiadbench_3038,1.000,4,4,8192.00
olympiadbench_3040,0.750,3,4,8192.00
olympiadbench_3035,1.000,4,4,8192.00
olympiadbench_3034,0.000,0,4,8192.00
olympiadbench_3029,0.500,2,4,8193.50
olympiadbench_3047,1.000,4,4,8192.00
olympiadbench_3036,1.000,4,4,8192.00
olympiadbench_3046,1.000,4,4,8192.00
olympiadbench_3039,0.000,0,4,8192.00
olympiadbench_3044,1.000,4,4,8192.00
olympiadbench_3043,0.000,0,4,8192.00
olympiadbench_3045,0.750,3,4,8192.00
olympiadbench_3041,0.250,1,4,8192.00
olympiadbench_3077,0.500,2,4,8192.00
olympiadbench_3049,0.750,3,4,8192.00
olympiadbench_3078,1.000,4,4,8192.00
olympiadbench_3042,0.250,1,4,8192.00
olympiadbench_3048,0.500,2,4,8192.00
olympiadbench_3075,0.000,0,4,8192.00
olympiadbench_3079,0.000,0,4,8192.00
olympiadbench_3076,0.000,0,4,8192.00
olympiadbench_3089,1.000,4,4,8192.00
olympiadbench_3080,0.000,0,4,8192.00
olympiadbench_3084,0.750,3,4,8192.00
olympiadbench_3090,1.000,4,4,8192.00
olympiadbench_3081,0.000,0,4,8192.00
olympiadbench_3091,1.000,4,4,8192.00
olympiadbench_3083,0.000,0,4,8192.00
olympiadbench_3096,1.000,4,4,8192.00
olympiadbench_3082,0.000,0,4,8192.00
olympiadbench_3092,1.000,4,4,8192.00
olympiadbench_3101,1.000,4,4,8192.00
olympiadbench_3085,0.000,0,4,8192.00
olympiadbench_3094,0.000,0,4,8192.00
olympiadbench_3087,0.000,0,4,8192.00
olympiadbench_3102,1.000,4,4,8192.00
olympiadbench_3088,0.500,2,4,8192.00
olympiadbench_3098,1.000,4,4,8192.00
olympiadbench_3099,1.000,4,4,8192.00
olympiadbench_3100,1.000,4,4,8192.00
olympiadbench_3095,0.000,0,4,8192.00
olympiadbench_3086,0.000,0,4,8192.00
olympiadbench_3097,1.000,4,4,8192.00
Total Accuracy,0.381,1028,2700,8191.90
1 problem_id accuracy correct_count total_samples avg_output_length
2 olympiadbench_1750 0.000 0 4 8192.00
3 olympiadbench_1620 0.000 0 4 8192.00
4 olympiadbench_1697 0.000 0 4 8192.00
5 olympiadbench_1709 0.000 0 4 8191.75
6 olympiadbench_1618 0.000 0 4 8192.00
7 olympiadbench_1760 0.000 0 4 8192.00
8 olympiadbench_1644 0.000 0 4 8192.00
9 olympiadbench_1695 0.000 0 4 8192.00
10 olympiadbench_1645 0.000 0 4 8192.00
11 olympiadbench_1694 0.000 0 4 8192.00
12 olympiadbench_1678 0.000 0 4 8192.00
13 olympiadbench_1606 0.250 1 4 8192.00
14 olympiadbench_1687 0.000 0 4 8192.00
15 olympiadbench_1631 0.000 0 4 8192.00
16 olympiadbench_1718 0.000 0 4 8192.00
17 olympiadbench_1736 0.000 0 4 8192.00
18 olympiadbench_1747 0.000 0 4 8192.00
19 olympiadbench_1737 0.000 0 4 8192.00
20 olympiadbench_1659 0.250 1 4 8192.00
21 olympiadbench_1675 0.500 2 4 8192.00
22 olympiadbench_1681 0.250 1 4 8192.00
23 olympiadbench_1724 0.000 0 4 8192.00
24 olympiadbench_1613 0.250 1 4 8192.00
25 olympiadbench_1723 0.000 0 4 8192.00
26 olympiadbench_1612 0.000 0 4 8192.00
27 olympiadbench_1664 0.000 0 4 8192.00
28 olympiadbench_1716 0.000 0 4 8192.00
29 olympiadbench_1610 0.000 0 4 8192.00
30 olympiadbench_1641 0.000 0 4 8192.00
31 olympiadbench_1738 0.000 0 4 8192.00
32 olympiadbench_1662 0.000 0 4 8192.00
33 olympiadbench_1614 0.000 0 4 8192.00
34 olympiadbench_1766 0.000 0 4 8192.00
35 olympiadbench_1789 0.000 0 4 8192.00
36 olympiadbench_1818 0.000 0 4 8192.00
37 olympiadbench_1810 0.000 0 4 8192.00
38 olympiadbench_1866 0.250 1 4 8192.00
39 olympiadbench_1828 0.000 0 4 8192.00
40 olympiadbench_1807 0.000 0 4 8192.00
41 olympiadbench_1775 0.000 0 4 8192.00
42 olympiadbench_1798 0.250 1 4 8192.00
43 olympiadbench_1800 0.000 0 4 8192.00
44 olympiadbench_1820 0.000 0 4 8192.00
45 olympiadbench_1843 0.500 2 4 8192.00
46 olympiadbench_1833 0.000 0 4 8192.00
47 olympiadbench_1854 0.000 0 4 8191.75
48 olympiadbench_1832 0.000 0 4 8192.00
49 olympiadbench_1845 0.000 0 4 8192.00
50 olympiadbench_1869 0.000 0 4 8192.00
51 olympiadbench_1834 0.250 1 4 8192.00
52 olympiadbench_1782 0.000 0 4 8191.00
53 olympiadbench_1883 0.000 0 4 8192.00
54 olympiadbench_1872 0.000 0 4 8192.00
55 olympiadbench_1874 0.000 0 4 8192.00
56 olympiadbench_1879 0.000 0 4 8192.00
57 olympiadbench_1847 0.250 1 4 8192.00
58 olympiadbench_1915 0.000 0 4 8192.00
59 olympiadbench_1838 0.000 0 4 8192.00
60 olympiadbench_1887 0.000 0 4 8192.00
61 olympiadbench_1873 0.000 0 4 8191.50
62 olympiadbench_1918 0.000 0 4 8192.00
63 olympiadbench_1914 0.000 0 4 8192.00
64 olympiadbench_1882 0.000 0 4 8192.00
65 olympiadbench_1920 0.000 0 4 8192.00
66 olympiadbench_1929 0.250 1 4 8192.00
67 olympiadbench_1930 0.000 0 4 8192.00
68 olympiadbench_1938 0.000 0 4 8192.00
69 olympiadbench_1964 0.000 0 4 8192.00
70 olympiadbench_1965 0.000 0 4 8192.00
71 olympiadbench_1940 0.000 0 4 8192.00
72 olympiadbench_1962 0.000 0 4 8192.00
73 olympiadbench_1939 0.000 0 4 8192.00
74 olympiadbench_1969 0.000 0 4 8192.00
75 olympiadbench_1974 0.000 0 4 8192.00
76 olympiadbench_1945 0.000 0 4 8191.75
77 olympiadbench_1953 0.000 0 4 8192.00
78 olympiadbench_1988 0.000 0 4 8192.00
79 olympiadbench_2004 0.000 0 4 8179.75
80 olympiadbench_2000 0.000 0 4 8192.00
81 olympiadbench_1970 0.000 0 4 8192.00
82 olympiadbench_1968 0.250 1 4 8192.00
83 olympiadbench_1997 0.000 0 4 8192.00
84 olympiadbench_1977 0.000 0 4 8191.75
85 olympiadbench_2012 0.000 0 4 8192.00
86 olympiadbench_2006 0.000 0 4 8192.00
87 olympiadbench_2024 0.000 0 4 8192.00
88 olympiadbench_2010 0.000 0 4 8192.00
89 olympiadbench_1998 0.000 0 4 8192.00
90 olympiadbench_2022 0.250 1 4 8192.00
91 olympiadbench_2035 0.000 0 4 8192.00
92 olympiadbench_2021 0.000 0 4 8192.00
93 olympiadbench_2037 0.000 0 4 8192.00
94 olympiadbench_2011 0.000 0 4 8192.00
95 olympiadbench_2032 0.000 0 4 8192.00
96 olympiadbench_2029 0.750 3 4 8192.00
97 olympiadbench_2040 0.000 0 4 8192.00
98 olympiadbench_2099 0.000 0 4 8191.25
99 olympiadbench_2082 0.000 0 4 8192.00
100 olympiadbench_2084 0.000 0 4 8192.00
101 olympiadbench_2075 0.000 0 4 8192.00
102 olympiadbench_2111 0.000 0 4 8192.00
103 olympiadbench_2064 0.000 0 4 8192.00
104 olympiadbench_2095 0.000 0 4 8192.00
105 olympiadbench_2151 0.000 0 4 8192.00
106 olympiadbench_2063 0.000 0 4 8192.00
107 olympiadbench_2045 0.000 0 4 8192.00
108 olympiadbench_2177 0.500 2 4 8192.00
109 olympiadbench_2147 0.000 0 4 8192.00
110 olympiadbench_2165 0.000 0 4 8192.00
111 olympiadbench_2124 0.250 1 4 8192.00
112 olympiadbench_2126 0.000 0 4 8192.00
113 olympiadbench_2091 0.000 0 4 8192.00
114 olympiadbench_2153 0.000 0 4 8192.00
115 olympiadbench_2171 0.000 0 4 8192.00
116 olympiadbench_2152 0.000 0 4 8192.00
117 olympiadbench_2193 0.000 0 4 8192.00
118 olympiadbench_2127 0.000 0 4 8192.00
119 olympiadbench_2174 0.000 0 4 8192.00
120 olympiadbench_2198 0.000 0 4 8192.00
121 olympiadbench_2203 0.000 0 4 8192.00
122 olympiadbench_2235 1.000 4 4 8192.00
123 olympiadbench_2185 0.000 0 4 8192.00
124 olympiadbench_2204 0.000 0 4 8192.00
125 olympiadbench_2230 0.000 0 4 8192.00
126 olympiadbench_2236 1.000 4 4 8192.00
127 olympiadbench_2239 0.500 2 4 8191.75
128 olympiadbench_2212 0.000 0 4 8191.75
129 olympiadbench_2216 0.000 0 4 8192.00
130 olympiadbench_2248 1.000 4 4 8192.00
131 olympiadbench_2242 1.000 4 4 8192.00
132 olympiadbench_2234 1.000 4 4 8192.00
133 olympiadbench_2241 1.000 4 4 8192.00
134 olympiadbench_2238 1.000 4 4 8193.50
135 olympiadbench_2251 0.750 3 4 8192.00
136 olympiadbench_2247 1.000 4 4 8192.00
137 olympiadbench_2258 0.250 1 4 8192.00
138 olympiadbench_2243 1.000 4 4 8192.00
139 olympiadbench_2253 0.500 2 4 8192.00
140 olympiadbench_2261 0.500 2 4 8192.00
141 olympiadbench_2256 1.000 4 4 8192.00
142 olympiadbench_2249 1.000 4 4 8192.00
143 olympiadbench_2260 0.500 2 4 8192.00
144 olympiadbench_2265 0.500 2 4 8192.00
145 olympiadbench_2268 1.000 4 4 8192.00
146 olympiadbench_2257 0.750 3 4 8192.00
147 olympiadbench_2276 0.000 0 4 8192.00
148 olympiadbench_2254 0.000 0 4 8192.00
149 olympiadbench_2255 0.000 0 4 8192.00
150 olympiadbench_2266 1.000 4 4 8192.00
151 olympiadbench_2280 1.000 4 4 8192.00
152 olympiadbench_2288 0.250 1 4 8192.00
153 olympiadbench_2281 1.000 4 4 8192.00
154 olympiadbench_2277 1.000 4 4 8192.00
155 olympiadbench_2275 0.250 1 4 8192.00
156 olympiadbench_2263 1.000 4 4 8192.00
157 olympiadbench_2286 1.000 4 4 8192.00
158 olympiadbench_2282 0.750 3 4 8192.00
159 olympiadbench_2292 1.000 4 4 8192.00
160 olympiadbench_2287 0.500 2 4 8192.00
161 olympiadbench_2283 0.000 0 4 8192.00
162 olympiadbench_2289 1.000 4 4 8192.00
163 olympiadbench_2303 0.000 0 4 8192.00
164 olympiadbench_2300 1.000 4 4 8192.00
165 olympiadbench_2322 1.000 4 4 8192.00
166 olympiadbench_2312 1.000 4 4 8192.00
167 olympiadbench_2313 0.750 3 4 8192.00
168 olympiadbench_2325 0.000 0 4 8192.00
169 olympiadbench_2298 0.000 0 4 8192.00
170 olympiadbench_2327 0.750 3 4 8192.00
171 olympiadbench_2315 0.250 1 4 8192.00
172 olympiadbench_2317 1.000 4 4 8192.00
173 olympiadbench_2328 1.000 4 4 8192.00
174 olympiadbench_2301 0.000 0 4 8192.00
175 olympiadbench_2323 0.750 3 4 8192.00
176 olympiadbench_2329 1.000 4 4 8192.00
177 olympiadbench_2321 1.000 4 4 8192.00
178 olympiadbench_2319 0.000 0 4 8192.00
179 olympiadbench_2331 1.000 4 4 8192.00
180 olympiadbench_2326 1.000 4 4 8192.00
181 olympiadbench_2332 0.750 3 4 8192.00
182 olympiadbench_2318 0.000 0 4 8192.00
183 olympiadbench_2339 1.000 4 4 8192.00
184 olympiadbench_2343 1.000 4 4 8192.00
185 olympiadbench_2334 0.250 1 4 8192.00
186 olympiadbench_2330 0.250 1 4 8192.00
187 olympiadbench_2336 0.000 0 4 8192.00
188 olympiadbench_2345 1.000 4 4 8192.00
189 olympiadbench_2338 1.000 4 4 8192.00
190 olympiadbench_2333 0.000 0 4 8190.50
191 olympiadbench_2351 1.000 4 4 8192.00
192 olympiadbench_2340 0.750 3 4 8192.00
193 olympiadbench_2344 0.750 3 4 8192.00
194 olympiadbench_2352 1.000 4 4 8192.00
195 olympiadbench_2342 1.000 4 4 8192.00
196 olympiadbench_2341 0.000 0 4 8192.00
197 olympiadbench_2346 1.000 4 4 8192.00
198 olympiadbench_2349 0.000 0 4 8192.00
199 olympiadbench_2371 1.000 4 4 8192.00
200 olympiadbench_2359 1.000 4 4 8192.00
201 olympiadbench_2369 1.000 4 4 8192.00
202 olympiadbench_2356 0.000 0 4 8192.00
203 olympiadbench_2355 0.500 2 4 8192.00
204 olympiadbench_2361 0.250 1 4 8192.00
205 olympiadbench_2376 1.000 4 4 8192.00
206 olympiadbench_2350 0.000 0 4 8192.00
207 olympiadbench_2375 0.500 2 4 8192.00
208 olympiadbench_2388 1.000 4 4 8192.00
209 olympiadbench_2370 0.750 3 4 8192.50
210 olympiadbench_2372 1.000 4 4 8192.00
211 olympiadbench_2391 1.000 4 4 8192.00
212 olympiadbench_2403 1.000 4 4 8192.00
213 olympiadbench_2380 0.000 0 4 8191.25
214 olympiadbench_2390 1.000 4 4 8192.00
215 olympiadbench_2392 0.750 3 4 8192.00
216 olympiadbench_2397 1.000 4 4 8192.00
217 olympiadbench_2382 0.500 2 4 8192.00
218 olympiadbench_2377 0.000 0 4 8192.00
219 olympiadbench_2409 0.500 2 4 8192.00
220 olympiadbench_2410 1.000 4 4 8192.00
221 olympiadbench_2420 1.000 4 4 8192.00
222 olympiadbench_2384 0.000 0 4 8192.00
223 olympiadbench_2419 1.000 4 4 8192.00
224 olympiadbench_2407 0.000 0 4 8192.00
225 olympiadbench_2421 1.000 4 4 8192.00
226 olympiadbench_2408 0.250 1 4 8192.00
227 olympiadbench_2414 0.500 2 4 8192.00
228 olympiadbench_2425 1.000 4 4 8192.00
229 olympiadbench_2415 0.000 0 4 8192.00
230 olympiadbench_2423 0.500 2 4 8191.75
231 olympiadbench_2431 1.000 4 4 8192.00
232 olympiadbench_2426 0.250 1 4 8192.00
233 olympiadbench_2438 1.000 4 4 8192.00
234 olympiadbench_2435 0.500 2 4 8192.00
235 olympiadbench_2427 0.750 3 4 8192.00
236 olympiadbench_2422 0.750 3 4 8192.00
237 olympiadbench_2439 1.000 4 4 8192.00
238 olympiadbench_2432 0.250 1 4 8192.00
239 olympiadbench_2445 1.000 4 4 8192.50
240 olympiadbench_2444 1.000 4 4 8192.00
241 olympiadbench_2443 1.000 4 4 8192.00
242 olympiadbench_2441 0.500 2 4 8192.00
243 olympiadbench_2430 0.250 1 4 8192.00
244 olympiadbench_2458 1.000 4 4 8192.00
245 olympiadbench_2459 1.000 4 4 8192.00
246 olympiadbench_2442 0.000 0 4 8191.50
247 olympiadbench_2466 1.000 4 4 8192.00
248 olympiadbench_2454 1.000 4 4 8192.00
249 olympiadbench_2440 0.500 2 4 8192.00
250 olympiadbench_2453 0.000 0 4 8186.00
251 olympiadbench_2469 0.750 3 4 8191.75
252 olympiadbench_2460 0.500 2 4 8192.00
253 olympiadbench_2467 0.000 0 4 8192.00
254 olympiadbench_2461 0.000 0 4 8192.00
255 olympiadbench_2482 0.500 2 4 8192.00
256 olympiadbench_2479 1.000 4 4 8192.00
257 olympiadbench_2481 0.750 3 4 8192.00
258 olympiadbench_2463 0.000 0 4 8192.00
259 olympiadbench_2464 0.000 0 4 8192.00
260 olympiadbench_2472 0.000 0 4 8192.00
261 olympiadbench_2475 0.000 0 4 8192.00
262 olympiadbench_2492 1.000 4 4 8192.00
263 olympiadbench_2498 0.000 0 4 8192.00
264 olympiadbench_2494 1.000 4 4 8191.75
265 olympiadbench_2500 1.000 4 4 8192.00
266 olympiadbench_2489 0.000 0 4 8192.00
267 olympiadbench_2486 0.000 0 4 8192.00
268 olympiadbench_2496 0.750 3 4 8192.00
269 olympiadbench_2506 0.750 3 4 8192.00
270 olympiadbench_2508 1.000 4 4 8192.00
271 olympiadbench_2509 0.750 3 4 8192.00
272 olympiadbench_2501 0.000 0 4 8192.00
273 olympiadbench_2493 0.250 1 4 8192.00
274 olympiadbench_2504 1.000 4 4 8192.00
275 olympiadbench_2490 0.000 0 4 8192.00
276 olympiadbench_2502 0.500 2 4 8192.00
277 olympiadbench_2520 1.000 4 4 8192.00
278 olympiadbench_2510 0.750 3 4 8192.00
279 olympiadbench_2507 0.000 0 4 8189.75
280 olympiadbench_2531 1.000 4 4 8192.00
281 olympiadbench_2523 0.500 2 4 8191.75
282 olympiadbench_2532 0.750 3 4 8192.00
283 olympiadbench_2521 0.500 2 4 8192.00
284 olympiadbench_2536 1.000 4 4 8193.00
285 olympiadbench_2524 0.500 2 4 8192.00
286 olympiadbench_2548 1.000 4 4 8192.00
287 olympiadbench_2539 0.250 1 4 8192.00
288 olympiadbench_2527 0.500 2 4 8192.00
289 olympiadbench_2545 0.500 2 4 8192.00
290 olympiadbench_2522 0.000 0 4 8192.00
291 olympiadbench_2552 1.000 4 4 8192.00
292 olympiadbench_2544 0.000 0 4 8192.00
293 olympiadbench_2534 0.500 2 4 8192.00
294 olympiadbench_2549 0.000 0 4 8192.00
295 olympiadbench_2551 0.250 1 4 8192.00
296 olympiadbench_2525 0.000 0 4 8189.75
297 olympiadbench_2553 1.000 4 4 8192.00
298 olympiadbench_2560 0.500 2 4 8192.00
299 olympiadbench_2558 0.250 1 4 8192.00
300 olympiadbench_2568 1.000 4 4 8192.50
301 olympiadbench_2575 0.500 2 4 8192.00
302 olympiadbench_2578 1.000 4 4 8192.00
303 olympiadbench_2555 0.000 0 4 8192.00
304 olympiadbench_2565 0.000 0 4 8192.00
305 olympiadbench_2570 1.000 4 4 8192.00
306 olympiadbench_2569 0.750 3 4 8192.00
307 olympiadbench_2571 0.750 3 4 8192.00
308 olympiadbench_2559 0.750 3 4 8192.00
309 olympiadbench_2574 0.000 0 4 8192.00
310 olympiadbench_2577 0.500 2 4 8192.00
311 olympiadbench_2576 0.250 1 4 8192.00
312 olympiadbench_2572 0.250 1 4 8192.00
313 olympiadbench_2596 1.000 4 4 8192.00
314 olympiadbench_2584 0.000 0 4 8192.00
315 olympiadbench_2588 0.000 0 4 8192.00
316 olympiadbench_2580 0.500 2 4 8192.00
317 olympiadbench_2582 0.250 1 4 8192.00
318 olympiadbench_2583 0.500 2 4 8191.75
319 olympiadbench_2592 0.500 2 4 8192.00
320 olympiadbench_2598 0.750 3 4 8192.00
321 olympiadbench_2599 0.750 3 4 8192.00
322 olympiadbench_2606 0.000 0 4 8192.00
323 olympiadbench_2601 0.500 2 4 8192.00
324 olympiadbench_2603 0.000 0 4 8192.00
325 olympiadbench_2609 1.000 4 4 8192.00
326 olympiadbench_2604 0.000 0 4 8192.00
327 olympiadbench_2602 0.000 0 4 8191.75
328 olympiadbench_2608 0.500 2 4 8192.00
329 olympiadbench_2607 0.000 0 4 8192.00
330 olympiadbench_2626 0.000 0 4 8191.50
331 olympiadbench_2610 0.000 0 4 8192.00
332 olympiadbench_2600 0.000 0 4 8187.75
333 olympiadbench_2613 0.500 2 4 8192.00
334 olympiadbench_2637 1.000 4 4 8191.75
335 olympiadbench_2615 0.500 2 4 8192.00
336 olympiadbench_2635 0.000 0 4 8192.00
337 olympiadbench_2614 0.500 2 4 8192.00
338 olympiadbench_2612 0.000 0 4 8192.00
339 olympiadbench_2611 0.000 0 4 8192.00
340 olympiadbench_2636 1.000 4 4 8192.00
341 olympiadbench_2642 0.250 1 4 8192.00
342 olympiadbench_2625 0.000 0 4 8192.00
343 olympiadbench_2641 0.500 2 4 8192.00
344 olympiadbench_2650 1.000 4 4 8192.00
345 olympiadbench_2639 0.000 0 4 8192.00
346 olympiadbench_2647 0.000 0 4 8192.00
347 olympiadbench_2638 0.250 1 4 8192.00
348 olympiadbench_2648 1.000 4 4 8192.00
349 olympiadbench_2645 0.000 0 4 8192.00
350 olympiadbench_2644 0.250 1 4 8192.00
351 olympiadbench_2640 0.000 0 4 8192.00
352 olympiadbench_2652 1.000 4 4 8192.00
353 olympiadbench_2646 0.000 0 4 8192.00
354 olympiadbench_2653 1.000 4 4 8192.00
355 olympiadbench_2651 1.000 4 4 8192.00
356 olympiadbench_2657 1.000 4 4 8192.00
357 olympiadbench_2643 0.000 0 4 8192.00
358 olympiadbench_2649 0.500 2 4 8192.00
359 olympiadbench_2656 1.000 4 4 8192.00
360 olympiadbench_2658 1.000 4 4 8192.00
361 olympiadbench_2659 0.500 2 4 8192.00
362 olympiadbench_2661 1.000 4 4 8192.00
363 olympiadbench_2655 0.000 0 4 8192.00
364 olympiadbench_2662 1.000 4 4 8192.00
365 olympiadbench_2663 0.000 0 4 8192.00
366 olympiadbench_2654 0.000 0 4 8192.00
367 olympiadbench_2660 0.500 2 4 8192.00
368 olympiadbench_2666 0.000 0 4 8192.00
369 olympiadbench_2675 0.000 0 4 8192.00
370 olympiadbench_2667 0.250 1 4 8192.00
371 olympiadbench_2664 0.000 0 4 8192.00
372 olympiadbench_2665 0.000 0 4 8193.50
373 olympiadbench_2669 1.000 4 4 8192.00
374 olympiadbench_2670 0.000 0 4 8192.00
375 olympiadbench_2673 0.000 0 4 8192.00
376 olympiadbench_2684 0.250 1 4 8192.00
377 olympiadbench_2668 0.000 0 4 8192.00
378 olympiadbench_2671 0.500 2 4 8192.00
379 olympiadbench_2674 0.750 3 4 8192.00
380 olympiadbench_2678 0.500 2 4 8192.00
381 olympiadbench_2679 0.500 2 4 8192.00
382 olympiadbench_2687 0.000 0 4 8192.00
383 olympiadbench_2702 0.250 1 4 8192.00
384 olympiadbench_2676 0.000 0 4 8192.00
385 olympiadbench_2701 0.750 3 4 8192.00
386 olympiadbench_2677 0.000 0 4 8192.00
387 olympiadbench_2672 0.000 0 4 8192.00
388 olympiadbench_2707 0.750 3 4 8191.75
389 olympiadbench_2680 0.500 2 4 8191.50
390 olympiadbench_2705 0.000 0 4 8192.00
391 olympiadbench_2708 1.000 4 4 8192.00
392 olympiadbench_2711 0.000 0 4 8192.00
393 olympiadbench_2713 0.000 0 4 8192.00
394 olympiadbench_2709 0.000 0 4 8192.00
395 olympiadbench_2706 0.000 0 4 8192.00
396 olympiadbench_2710 0.500 2 4 8192.00
397 olympiadbench_2712 0.000 0 4 8192.00
398 olympiadbench_2714 0.000 0 4 8192.00
399 olympiadbench_2720 0.750 3 4 8192.00
400 olympiadbench_2718 1.000 4 4 8192.00
401 olympiadbench_2723 0.000 0 4 8192.00
402 olympiadbench_2715 0.000 0 4 8192.00
403 olympiadbench_2717 0.000 0 4 8192.00
404 olympiadbench_2735 0.000 0 4 8192.00
405 olympiadbench_2721 0.000 0 4 8192.00
406 olympiadbench_2732 0.750 3 4 8192.00
407 olympiadbench_2727 0.000 0 4 8192.00
408 olympiadbench_2728 0.250 1 4 8192.00
409 olympiadbench_2722 0.000 0 4 8192.00
410 olympiadbench_2731 0.000 0 4 8192.00
411 olympiadbench_2733 0.000 0 4 8192.00
412 olympiadbench_2725 0.000 0 4 8191.75
413 olympiadbench_2724 0.000 0 4 8192.00
414 olympiadbench_2730 0.000 0 4 8192.00
415 olympiadbench_2729 0.000 0 4 8192.00
416 olympiadbench_2726 0.250 1 4 8192.00
417 olympiadbench_2739 0.000 0 4 8192.00
418 olympiadbench_2736 0.000 0 4 8192.00
419 olympiadbench_2738 0.500 2 4 8192.00
420 olympiadbench_2737 0.000 0 4 8192.00
421 olympiadbench_2747 1.000 4 4 8192.00
422 olympiadbench_2741 0.000 0 4 8180.25
423 olympiadbench_2742 0.000 0 4 8192.00
424 olympiadbench_2740 0.000 0 4 8192.00
425 olympiadbench_2746 0.750 3 4 8192.00
426 olympiadbench_2748 1.000 4 4 8192.00
427 olympiadbench_2734 0.000 0 4 8192.00
428 olympiadbench_2744 0.250 1 4 8192.00
429 olympiadbench_2753 0.000 0 4 8192.00
430 olympiadbench_2745 0.000 0 4 8192.00
431 olympiadbench_2754 0.000 0 4 8192.00
432 olympiadbench_2763 0.000 0 4 8192.00
433 olympiadbench_2759 0.000 0 4 8192.00
434 olympiadbench_2764 0.000 0 4 8192.00
435 olympiadbench_2773 1.000 4 4 8192.00
436 olympiadbench_2760 0.250 1 4 8192.00
437 olympiadbench_2765 0.000 0 4 8192.00
438 olympiadbench_2761 0.750 3 4 8192.00
439 olympiadbench_2777 1.000 4 4 8192.50
440 olympiadbench_2762 0.000 0 4 8192.00
441 olympiadbench_2776 1.000 4 4 8192.00
442 olympiadbench_2767 0.000 0 4 8192.00
443 olympiadbench_2775 0.500 2 4 8191.25
444 olympiadbench_2770 0.000 0 4 8192.00
445 olympiadbench_2780 1.000 4 4 8192.00
446 olympiadbench_2766 0.000 0 4 8192.00
447 olympiadbench_2768 0.000 0 4 8192.00
448 olympiadbench_2772 0.750 3 4 8192.00
449 olympiadbench_2783 1.000 4 4 8192.00
450 olympiadbench_2771 0.000 0 4 8192.00
451 olympiadbench_2781 1.000 4 4 8192.00
452 olympiadbench_2778 1.000 4 4 8192.00
453 olympiadbench_2782 0.750 3 4 8192.00
454 olympiadbench_2787 0.750 3 4 8191.25
455 olympiadbench_2785 1.000 4 4 8192.00
456 olympiadbench_2784 0.500 2 4 8192.00
457 olympiadbench_2788 0.000 0 4 8192.00
458 olympiadbench_2786 0.750 3 4 8192.00
459 olympiadbench_2790 0.500 2 4 8192.00
460 olympiadbench_2789 0.000 0 4 8192.00
461 olympiadbench_2791 0.750 3 4 8192.00
462 olympiadbench_2792 0.000 0 4 8192.00
463 olympiadbench_2799 1.000 4 4 8192.00
464 olympiadbench_2793 0.000 0 4 8192.00
465 olympiadbench_2795 0.000 0 4 8192.00
466 olympiadbench_2827 0.000 0 4 8192.00
467 olympiadbench_2798 0.750 3 4 8189.25
468 olympiadbench_2823 1.000 4 4 8192.00
469 olympiadbench_2830 1.000 4 4 8192.00
470 olympiadbench_2800 0.000 0 4 8192.00
471 olympiadbench_2796 0.000 0 4 8192.00
472 olympiadbench_2794 0.000 0 4 8192.25
473 olympiadbench_2797 0.750 3 4 8191.75
474 olympiadbench_2831 1.000 4 4 8192.00
475 olympiadbench_2829 0.000 0 4 8192.00
476 olympiadbench_2802 0.250 1 4 8192.00
477 olympiadbench_2801 0.000 0 4 8192.00
478 olympiadbench_2817 0.250 1 4 8192.00
479 olympiadbench_2824 0.000 0 4 8192.00
480 olympiadbench_2821 0.000 0 4 8192.00
481 olympiadbench_2819 0.000 0 4 8192.00
482 olympiadbench_2818 1.000 4 4 8192.00
483 olympiadbench_2834 1.000 4 4 8192.00
484 olympiadbench_2822 0.000 0 4 8191.75
485 olympiadbench_2828 0.500 2 4 8192.00
486 olympiadbench_2836 1.000 4 4 8192.00
487 olympiadbench_2825 0.000 0 4 8192.50
488 olympiadbench_2839 0.250 1 4 8192.00
489 olympiadbench_2840 0.500 2 4 8192.00
490 olympiadbench_2842 1.000 4 4 8191.75
491 olympiadbench_2838 1.000 4 4 8192.00
492 olympiadbench_2841 0.500 2 4 8192.00
493 olympiadbench_2832 0.000 0 4 8192.00
494 olympiadbench_2835 0.750 3 4 8192.00
495 olympiadbench_2843 0.000 0 4 8192.00
496 olympiadbench_2845 0.500 2 4 8192.00
497 olympiadbench_2852 0.000 0 4 8192.00
498 olympiadbench_2846 0.250 1 4 8192.00
499 olympiadbench_2847 0.500 2 4 8192.00
500 olympiadbench_2849 0.750 3 4 8192.00
501 olympiadbench_2844 0.250 1 4 8191.75
502 olympiadbench_2848 0.750 3 4 8188.75
503 olympiadbench_2860 0.250 1 4 8192.00
504 olympiadbench_2850 0.000 0 4 8192.00
505 olympiadbench_2856 0.000 0 4 8192.00
506 olympiadbench_2853 0.750 3 4 8192.00
507 olympiadbench_2857 0.000 0 4 8192.00
508 olympiadbench_2854 0.000 0 4 8192.00
509 olympiadbench_2851 0.000 0 4 8192.00
510 olympiadbench_2858 0.500 2 4 8192.00
511 olympiadbench_2863 0.000 0 4 8192.00
512 olympiadbench_2855 0.000 0 4 8192.00
513 olympiadbench_2859 0.000 0 4 8192.00
514 olympiadbench_2861 0.000 0 4 8192.00
515 olympiadbench_2887 0.000 0 4 8192.00
516 olympiadbench_2890 0.500 2 4 8192.00
517 olympiadbench_2862 0.000 0 4 8192.00
518 olympiadbench_2898 1.000 4 4 8192.00
519 olympiadbench_2891 0.000 0 4 8192.00
520 olympiadbench_2888 0.000 0 4 8192.00
521 olympiadbench_2901 1.000 4 4 8192.00
522 olympiadbench_2892 0.000 0 4 8192.00
523 olympiadbench_2884 0.250 1 4 8191.75
524 olympiadbench_2903 0.750 3 4 8192.00
525 olympiadbench_2894 0.000 0 4 8192.00
526 olympiadbench_2893 0.000 0 4 8192.00
527 olympiadbench_2905 1.000 4 4 8192.00
528 olympiadbench_2895 0.000 0 4 8192.00
529 olympiadbench_2900 1.000 4 4 8192.00
530 olympiadbench_2896 0.000 0 4 8192.00
531 olympiadbench_2909 1.000 4 4 8192.00
532 olympiadbench_2904 1.000 4 4 8192.00
533 olympiadbench_2902 0.750 3 4 8192.00
534 olympiadbench_2899 0.750 3 4 8192.00
535 olympiadbench_2907 1.000 4 4 8192.00
536 olympiadbench_2911 1.000 4 4 8192.00
537 olympiadbench_2908 1.000 4 4 8192.00
538 olympiadbench_2897 0.000 0 4 8187.50
539 olympiadbench_2912 0.250 1 4 8192.00
540 olympiadbench_2910 0.500 2 4 8192.00
541 olympiadbench_2913 0.500 2 4 8192.00
542 olympiadbench_2914 0.000 0 4 8192.00
543 olympiadbench_2922 1.000 4 4 8192.00
544 olympiadbench_2920 0.000 0 4 8191.75
545 olympiadbench_2916 0.000 0 4 8192.00
546 olympiadbench_2918 0.500 2 4 8192.00
547 olympiadbench_2947 0.250 1 4 8191.25
548 olympiadbench_2915 0.250 1 4 8192.00
549 olympiadbench_2919 0.000 0 4 8187.25
550 olympiadbench_2917 0.000 0 4 8192.00
551 olympiadbench_2925 1.000 4 4 8192.00
552 olympiadbench_2951 0.000 0 4 8192.00
553 olympiadbench_2924 0.500 2 4 8192.00
554 olympiadbench_2927 1.000 4 4 8192.00
555 olympiadbench_2953 0.000 0 4 8192.00
556 olympiadbench_2921 0.000 0 4 8192.00
557 olympiadbench_2949 0.000 0 4 8192.00
558 olympiadbench_2926 1.000 4 4 8192.00
559 olympiadbench_2950 0.500 2 4 8191.50
560 olympiadbench_2948 0.250 1 4 8192.00
561 olympiadbench_2955 0.250 1 4 8191.50
562 olympiadbench_2963 1.000 4 4 8192.00
563 olympiadbench_2957 0.000 0 4 8192.00
564 olympiadbench_2952 0.000 0 4 8192.00
565 olympiadbench_2960 1.000 4 4 8192.00
566 olympiadbench_2954 0.000 0 4 8192.00
567 olympiadbench_2971 0.000 0 4 8192.00
568 olympiadbench_2958 0.000 0 4 8192.00
569 olympiadbench_2956 0.000 0 4 8192.00
570 olympiadbench_2966 0.750 3 4 8192.00
571 olympiadbench_2961 0.750 3 4 8192.00
572 olympiadbench_2972 1.000 4 4 8192.00
573 olympiadbench_2968 1.000 4 4 8192.00
574 olympiadbench_2962 0.250 1 4 8192.00
575 olympiadbench_2964 0.500 2 4 8192.00
576 olympiadbench_2970 1.000 4 4 8192.00
577 olympiadbench_2974 0.500 2 4 8192.00
578 olympiadbench_2967 0.000 0 4 8192.00
579 olympiadbench_2969 0.000 0 4 8192.00
580 olympiadbench_2985 0.750 3 4 8192.00
581 olympiadbench_2977 1.000 4 4 8192.00
582 olympiadbench_2975 0.250 1 4 8187.50
583 olympiadbench_2978 0.000 0 4 8192.00
584 olympiadbench_2973 0.000 0 4 8192.00
585 olympiadbench_2979 0.250 1 4 8192.00
586 olympiadbench_2986 0.750 3 4 8192.00
587 olympiadbench_2976 0.500 2 4 8192.00
588 olympiadbench_2984 0.000 0 4 8192.00
589 olympiadbench_2980 0.000 0 4 8192.00
590 olympiadbench_2983 0.000 0 4 8192.00
591 olympiadbench_2981 0.000 0 4 8192.00
592 olympiadbench_2982 0.000 0 4 8192.00
593 olympiadbench_2988 0.250 1 4 8192.00
594 olympiadbench_2987 0.000 0 4 8192.00
595 olympiadbench_2990 0.000 0 4 8192.00
596 olympiadbench_2989 1.000 4 4 8192.00
597 olympiadbench_3008 0.000 0 4 8192.00
598 olympiadbench_2994 0.000 0 4 8192.00
599 olympiadbench_2992 0.000 0 4 8192.00
600 olympiadbench_2991 0.750 3 4 8192.00
601 olympiadbench_2996 0.500 2 4 8192.00
602 olympiadbench_3011 0.000 0 4 8192.00
603 olympiadbench_3021 0.750 3 4 8192.00
604 olympiadbench_3013 0.500 2 4 8192.00
605 olympiadbench_2993 0.250 1 4 8192.00
606 olympiadbench_3015 0.000 0 4 8192.00
607 olympiadbench_2995 0.500 2 4 8192.00
608 olympiadbench_3006 0.000 0 4 8187.50
609 olympiadbench_3001 0.000 0 4 8192.00
610 olympiadbench_3000 0.000 0 4 8191.75
611 olympiadbench_3004 0.750 3 4 8192.00
612 olympiadbench_3007 0.000 0 4 8192.00
613 olympiadbench_3010 0.000 0 4 8192.00
614 olympiadbench_3019 1.000 4 4 8192.00
615 olympiadbench_3018 0.000 0 4 8192.00
616 olympiadbench_3012 0.000 0 4 8192.00
617 olympiadbench_3022 0.750 3 4 8192.00
618 olympiadbench_3016 0.000 0 4 8192.00
619 olympiadbench_3014 0.000 0 4 8192.00
620 olympiadbench_3024 1.000 4 4 8192.00
621 olympiadbench_3009 0.500 2 4 8192.00
622 olympiadbench_3020 0.500 2 4 8192.00
623 olympiadbench_3017 0.000 0 4 8192.00
624 olympiadbench_3028 1.000 4 4 8192.00
625 olympiadbench_3027 1.000 4 4 8192.00
626 olympiadbench_3030 1.000 4 4 8192.00
627 olympiadbench_3037 0.000 0 4 8192.00
628 olympiadbench_3033 1.000 4 4 8192.00
629 olympiadbench_3025 0.750 3 4 8192.00
630 olympiadbench_3031 1.000 4 4 8192.00
631 olympiadbench_3026 0.500 2 4 8191.50
632 olympiadbench_3023 0.250 1 4 8192.00
633 olympiadbench_3032 1.000 4 4 8192.00
634 olympiadbench_3038 1.000 4 4 8192.00
635 olympiadbench_3040 0.750 3 4 8192.00
636 olympiadbench_3035 1.000 4 4 8192.00
637 olympiadbench_3034 0.000 0 4 8192.00
638 olympiadbench_3029 0.500 2 4 8193.50
639 olympiadbench_3047 1.000 4 4 8192.00
640 olympiadbench_3036 1.000 4 4 8192.00
641 olympiadbench_3046 1.000 4 4 8192.00
642 olympiadbench_3039 0.000 0 4 8192.00
643 olympiadbench_3044 1.000 4 4 8192.00
644 olympiadbench_3043 0.000 0 4 8192.00
645 olympiadbench_3045 0.750 3 4 8192.00
646 olympiadbench_3041 0.250 1 4 8192.00
647 olympiadbench_3077 0.500 2 4 8192.00
648 olympiadbench_3049 0.750 3 4 8192.00
649 olympiadbench_3078 1.000 4 4 8192.00
650 olympiadbench_3042 0.250 1 4 8192.00
651 olympiadbench_3048 0.500 2 4 8192.00
652 olympiadbench_3075 0.000 0 4 8192.00
653 olympiadbench_3079 0.000 0 4 8192.00
654 olympiadbench_3076 0.000 0 4 8192.00
655 olympiadbench_3089 1.000 4 4 8192.00
656 olympiadbench_3080 0.000 0 4 8192.00
657 olympiadbench_3084 0.750 3 4 8192.00
658 olympiadbench_3090 1.000 4 4 8192.00
659 olympiadbench_3081 0.000 0 4 8192.00
660 olympiadbench_3091 1.000 4 4 8192.00
661 olympiadbench_3083 0.000 0 4 8192.00
662 olympiadbench_3096 1.000 4 4 8192.00
663 olympiadbench_3082 0.000 0 4 8192.00
664 olympiadbench_3092 1.000 4 4 8192.00
665 olympiadbench_3101 1.000 4 4 8192.00
666 olympiadbench_3085 0.000 0 4 8192.00
667 olympiadbench_3094 0.000 0 4 8192.00
668 olympiadbench_3087 0.000 0 4 8192.00
669 olympiadbench_3102 1.000 4 4 8192.00
670 olympiadbench_3088 0.500 2 4 8192.00
671 olympiadbench_3098 1.000 4 4 8192.00
672 olympiadbench_3099 1.000 4 4 8192.00
673 olympiadbench_3100 1.000 4 4 8192.00
674 olympiadbench_3095 0.000 0 4 8192.00
675 olympiadbench_3086 0.000 0 4 8192.00
676 olympiadbench_3097 1.000 4 4 8192.00
677 Total Accuracy 0.381 1028 2700 8191.90

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,13884038,62.771439163773145
2,2264074,10.236156322337962
3,1117532,5.05249927662037
4,4852756,21.939905237268515
Total Tokens,22118400,100.0
1 iter_count token_count percentage
2 1 13884038 62.771439163773145
3 2 2264074 10.236156322337962
4 3 1117532 5.05249927662037
5 4 4852756 21.939905237268515
6 Total Tokens 22118400 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@4": 0.5259,
"cons@4": 0.4459,
"avg@4": 0.3807,
"avg_output_length": 8191.9,
"num_problems": 675,
"num_samples": 2700,
"repeat_size": 4,
"avg_request_time": 120.6629,
"end_2_end_time": 2599.8234,
"token_throughtput": 8507.547,
"request_throught": 1.0385,
"avg_iter_count": 1.8616,
"total_concurrency": 128,
"failed_requests": 0
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4d201918d8dd472819a43f052bf506958fe03bb0090b1bf9d1ceacd50ce30806
size 68474575

View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.57.3"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60c4f561bac35fed952859648971c9485609200abf03fd1606df02846abae026
size 41963105

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a8cd88eca38d03f9138a3e09ba98087d63409930e91a2a38cc22b55bba599805
size 50356437

151388
checkpoint-3780/merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ecd6a154932b7a95930b21c9135d6c27a3d9409562e57bcbfe9d85cd5391a5ef
size 3441185608

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca386e78b6be393fd56231840cd79a713287e78e403f06107651c21ec1ec150a
size 1403

View File

@@ -0,0 +1,25 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>"
}

View File

@@ -0,0 +1,49 @@
{
"embedding_key": "model.embed_tokens",
"max_iter": 4,
"iter_decider": "Qwen3MLPIterDecider",
"input_updater": "Qwen3MLPUpdater",
"train_loss": "CombinedLoss",
"eval_loss": "NextTokenPredLoss",
"eval_iter_decider": "iter_decider",
"iter_label_generator": "DynamicIterLabelGenerator",
"iter_attention_mode": "duo",
"attn_implementation": "sdpa",
"iter_attention_impl": "triton",
"weighted_hidden_method": "stop_prob_mix",
"memory_lean_fp32_reductions": false,
"detach_cross_iter_kv": false,
"iter_decider_kwargs": {
"hidden_size": 2048,
"intermediate_size": 2048,
"threshold": 0.5,
"topk": 2048
},
"input_updater_kwargs": {
"hidden_size": 2048,
"intermediate_size": 2048
},
"train_loss_kwargs": {
"losses": [
{
"name": "NextTokenPredLoss",
"weight": 1.0
},
{
"name": "IterDeciderLoss",
"weight": 0.05,
"kwargs": {
"dyn_pos_weight": true,
"cost_sensitive": true,
"cost_aware": false
}
}
]
},
"eval_loss_kwargs": {},
"eval_iter_decider_kwargs": {},
"iter_label_generator_kwargs": {
"strategy": "posterior_ce",
"abs_improv_coverage": 0.99
}
}

BIN
checkpoint-3780/tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,241 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": {},
"fix_mistral_regex": true,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

File diff suppressed because one or more lines are too long