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 +1,321 @@
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