# Generation-parameter profiles (YAML).
# Usage: evalharness eval run <bench> --model ... --profile <name>
# Resolution: DatasetSpec.gen_config < profile.default < profile.<bench> < gen_kwargs

dp4-nothink:
  default: {temperature: 0.0, max_tokens: 32768, top_p: 1.0}

qwen3-es-parity:
  default: {temperature: 0.0, max_tokens: 32768}
  simple_qa: {max_tokens: 1024}
  hle: {max_tokens: 8192}
  gpqa_diamond: {temperature: 1.0, max_tokens: 8192}
  aime24: {temperature: 1.0, max_tokens: 8192}
  aime25: {temperature: 1.0, max_tokens: 8192}
  aime26: {temperature: 1.0, max_tokens: 8192}
  hmmt26: {temperature: 1.0, max_tokens: 8192}
  imo_answerbench: {temperature: 1.0, max_tokens: 8192}

glm53-nothink:
  default: {temperature: 0.0, max_tokens: 8192, top_p: 1.0}
  aime24: {temperature: 1.0, max_tokens: 8192}
  aime25: {temperature: 1.0, max_tokens: 8192}
  aime26: {temperature: 1.0, max_tokens: 8192}
  hmmt26: {temperature: 1.0, max_tokens: 8192}
  imo_answerbench: {temperature: 1.0, max_tokens: 8192}
  gpqa_diamond: {temperature: 1.0, max_tokens: 8192}
  humaneval: {temperature: 1.0, max_tokens: 32768}
  live_code_bench: {temperature: 1.0, max_tokens: 32768}

t1-short:
  default: {temperature: 1.0, max_tokens: 8192, top_p: 1.0}