model: Nanthasit/sakthai-plus-1.5b
benchmark_ts: '2026-07-31T04:36:34Z'
backend: llama.cpp-gguf-q4_k_m
quantization: q4_k_m
prompt_type: tool_calling_send_email
prompt_length_chars: 1290
prompt: '<|im_start|>system

  You are Qwen, created by Alibaba Cloud. You are a helpful assistant.


  # Tools


  Yo...'
trials: 3
total_time_s: 47.56
input_tokens: 308
avg_generation_tps: 20.7
has_tool_call_any: true
has_tool_call_all: true
has_valid_json_any: true
has_valid_json_all: true
has_correct_answer_any: true
has_correct_answer_all: true
trials_detail:
- seed: 7
  output_tokens: 63
  output_length: 231
  generation_tps: 20.9
  prompt_tps: 67.0
  has_tool_call: true
  has_valid_json: true
  has_correct_answer: true
  tool_name: send_email
  tool_args:
    to: Beer@Nanthasit.com
    subject: Plus 1.5B status
    body: Hi Beer, I wanted to check the benchmark results for the SakThai Plus model.
      Thanks!
  response_preview: '<tool_call>

    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the benchmark results
    for the SakThai Plus m'
- seed: 42
  output_tokens: 65
  output_length: 243
  generation_tps: 20.8
  prompt_tps: 71.0
  has_tool_call: true
  has_valid_json: true
  has_correct_answer: true
  tool_name: send_email
  tool_args:
    to: Beer@Nanthasit.com
    subject: Plus 1.5B status
    body: Hi Beer, I wanted to check the results for the SakThai Plus model. Everything
      looks good so far.
  response_preview: '<tool_call>

    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the results for the
    SakThai Plus model. Ever'
- seed: 1337
  output_tokens: 66
  output_length: 253
  generation_tps: 20.4
  prompt_tps: 70.5
  has_tool_call: true
  has_valid_json: true
  has_correct_answer: true
  tool_name: send_email
  tool_args:
    to: Beer@Nanthasit.com
    subject: Plus 1.5B status
    body: Hi Beer, I wanted to check the benchmark results for the SakThai Plus model.
      Everything looks good so far.
  response_preview: '<tool_call>

    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the benchmark results
    for the SakThai Plus m'
device: cpu
threads: 2
router_probe_status: 400
router_probe_error: Model not supported by provider hf-inference