default:
  temperature: 0.0
  top_p: 1.0
  stream: true
  max_tokens: 200336
aime24:
  temperature: 1.0
  repeats: 12
  max_tokens: 200336
aime25:
  temperature: 1.0
  repeats: 12
  max_tokens: 200336
aime26:
  temperature: 1.0
  repeats: 12
  max_tokens: 200336
hmmt26:
  temperature: 1.0
  repeats: 12
  max_tokens: 200336
imo_answerbench:
  temperature: 1.0
gpqa_diamond:
  temperature: 1.0
  repeats: 3
  max_tokens: 200336
mmlu:
  max_tokens: 200336
mmlu_pro:
  max_tokens: 200336
cmmlu:
  max_tokens: 200336
arc:
  max_tokens: 200336
hellaswag:
  max_tokens: 200336
winogrande:
  max_tokens: 200336
simple_qa:
  max_tokens: 200336
trivia_qa:
  max_tokens: 200336
humaneval:
  temperature: 1.0
  repeats: 3
live_code_bench:
  temperature: 1.0
longbench_v2:
  max_tokens: 200336
  max_input_tokens: 128000
openai_mrcr:
  max_tokens: 200336
  max_input_tokens: 128000
bfcl_v3:
  max_tokens: 4096
general_fc:
  max_tokens: 4096
tau2_bench:
  max_tokens: 16384

swe_bench_verified_agentic:
  max_tokens: 4096
  temperature: 0.0
  env: swe_agentic
  max_turns: 250