OpenCodePapers

agents-on-terminal-bench-science-0-1

Agents
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
GPT-6 Astra: A new generation of intelligence✓ Link64.6GPT-6 Astra2026-09-03
Introducing Claude Sonnet 5.5✓ Link59.9Claude Sonnet 5.5 (Claude Code)2026-09-28
Introducing Claude Opus 5.5✓ Link58.7Claude Opus 5.5 (Claude Code)2026-09-22
Introducing GPT-6.1 Sol57.02GPT-6.1 Sol2026-09-29
Introducing Claude Fable 5.1 and Claude Mythos 5.152.6Claude Fable 5.1 (max) (Claude Code)2026-09-01
Introducing Claude Haiku 5.520.6Claude Haiku 5.5 (max effort) (Claude Code)2026-10-07