OpenCodePapers

question-answering-on-officeqa-pro-preselected-text

Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Introducing Claude Fable 5.1 and Claude Mythos 5.169.0Claude Fable 5.1 (max effort, with fallbacks)2026-09-01
Introducing Claude Opus 5.5✓ Link67.7Claude Opus 5.5 (max effort)2026-09-22
Introducing Claude Sonnet 5.5✓ Link65.6Claude Sonnet 5.5 (max effort)2026-09-28
Introducing Claude Haiku 5.560.3Claude Haiku 5.5 (max effort)2026-10-07
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution48.87WorkRover-35B-A3B (Claude Code)2026-10-13