gpqa_diamond:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
hle:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
aime24:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
aime25:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 65536
    max_completion_tokens: 64000
mmlu_pro:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
simple_qa:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
arc:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
bbh:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
live_code_bench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 65536
    max_completion_tokens: 64000
  dataset_args:
    subset_list:
    - release_v6
aime26:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 65536
    max_completion_tokens: 64000
hmmt26:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
imo_answerbench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
super_gpqa:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
drop:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
hellaswag:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
mmlu:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
openai_mrcr:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
bigcodebench:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
humaneval:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
gsm8k:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
competition_math:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
cmmlu:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
trivia_qa:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
winogrande:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
longbench_v2:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 8192
    max_completion_tokens: 64000
  dataset_args:
    subset_list:
    - short
    - medium
    - long
tau2_bench:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 16384
    max_completion_tokens: 64000
  dataset_args:
    extra_params:
      user_model: deepseek-v4-pro
      api_key: sk-9ed86ef546ca47e3afa7c3b014dea268
      api_base: https://api.deepseek.com/v1
      generation_config:
        temperature: 0.0
        max_tokens: 4096
        max_completion_tokens: 64000
  agent_config:
    mode: native
    strategy: react
    max_steps: 50
general_fc:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 4096
    max_completion_tokens: 64000
bfcl_v3:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 4096
    max_completion_tokens: 64000
    parallel_tool_calls: true
  dataset_args:
    extra_params:
      is_fc_model: true
      underscore_to_dot: true
swe_bench_verified:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000
swe_bench_pro:
  generation_config:
    temperature: 0.0
    top_p: 1.0
    stream: true
    max_tokens: 32768
    max_completion_tokens: 64000