14 Révisions (f17c0af5d704ac9d15d27a3bb8e91f1dfe15c832)

Auteur SHA1 Message Date
  orangels f17c0af5d7 feat: tighten aime final answer parsing il y a 1 semaine
  orangels e0aca08f36 feat: align gpqa scoring with simple evals il y a 1 semaine
  orangels 898d02f7ef feat: record upstream error debug payloads il y a 1 semaine
  orangels 5706ac8ee8 feat: add google gemini protocol il y a 1 semaine
  orangels 18cc7ff716 feat: add provider thinking parameters il y a 2 semaines
  orangels ee13739c5e feat: add raw response debug mode il y a 2 semaines
  orangels e269f8f99d docs: add end-to-end testing guide for RPM and benchmarks il y a 2 semaines
  orangels f5b9239167 docs: add Chinese usage guide il y a 2 semaines
  orangels f6b09d00a4 docs: plan rpm limiter modes il y a 2 semaines
  orangels 4a0e187e98 docs: specify benchmark report output il y a 2 semaines
  orangels ea0b255547 docs: add implementation plan il y a 2 semaines
  orangels 61446dcf9f docs: define benchmark dataset download flow il y a 2 semaines
  orangels 6e804b917f docs: use official gsm8k benchmark il y a 2 semaines
  orangels 884097722f docs: add design spec il y a 2 semaines