terminal_bench_v2:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    max_steps: 500
    per_step_tokens: 49152

gpqa_diamond:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

hle:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

aime24:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

aime25:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

mmlu_pro:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

simple_qa:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

arc:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

bbh:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

browsecomp:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 49152
    max_steps: 500

live_code_bench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  dataset_args:
    subset_list:
      - release_v6

swe_bench_pro:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 32768
    max_steps: 500

aime26:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

hmmt26:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

imo_answerbench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    max_steps: 500

super_gpqa:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

drop:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

hellaswag:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

mmlu:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

openai_mrcr:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

mcp_atlas:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 49152
    max_steps: 500

swe_bench_multilingual_agentic:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 32768
    max_steps: 500

swe_bench_verified:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 32768
    max_steps: 500

bigcodebench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288

humaneval:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288

gsm8k:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

competition_math:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

cmmlu:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

trivia_qa:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

winogrande:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

longbench_v2:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 131072

tau2_bench:
  generation_config:
    temperature: 1.0
    top_p: 1.0
    stream: true
    max_tokens: 524288
  agent_config:
    per_step_tokens: 32768
    max_steps: 500