# 低思考档：全库参数同 default.yaml，仅追加 reasoning_effort: low
# 用法: evalharness eval run ... --config effort_low
default:
  temperature: 0.0
  top_p: 1.0
  stream: true
  max_tokens: 32768
  reasoning_effort: low
aime24:
  temperature: 1.0
  repeats: 12
  max_tokens: 8192
  reasoning_effort: low
aime25:
  temperature: 1.0
  repeats: 12
  max_tokens: 8192
  reasoning_effort: low
aime26:
  temperature: 1.0
  repeats: 12
  max_tokens: 8192
  reasoning_effort: low
hmmt26:
  temperature: 1.0
  repeats: 12
  max_tokens: 8192
  reasoning_effort: low
imo_answerbench:
  temperature: 1.0
  reasoning_effort: low
gpqa_diamond:
  temperature: 1.0
  repeats: 3
  max_tokens: 8192
  reasoning_effort: low
mmlu:
  max_tokens: 8192
  reasoning_effort: low
mmlu_pro:
  max_tokens: 8192
  reasoning_effort: low
cmmlu:
  max_tokens: 8192
  reasoning_effort: low
arc:
  max_tokens: 8192
  reasoning_effort: low
hellaswag:
  max_tokens: 8192
  reasoning_effort: low
winogrande:
  max_tokens: 8192
  reasoning_effort: low
simple_qa:
  max_tokens: 8192
  reasoning_effort: low
trivia_qa:
  max_tokens: 8192
  reasoning_effort: low
humaneval:
  temperature: 1.0
  repeats: 3
  reasoning_effort: low
live_code_bench:
  temperature: 1.0
  reasoning_effort: low
longbench_v2:
  max_tokens: 8192
  max_input_tokens: 128000
  reasoning_effort: low
openai_mrcr:
  max_tokens: 8192
  max_input_tokens: 128000
  reasoning_effort: low
bfcl_v3:
  max_tokens: 4096
  reasoning_effort: low
general_fc:
  max_tokens: 4096
  reasoning_effort: low
tau2_bench:
  max_tokens: 16384
  reasoning_effort: low