Science's Last Exam: best AI agent scores 37.5/100, all score 0 on end-to-end research
omarsar0 · x · 2026-11-06
The AItonomy Foundation launched Science's Last Exam (SLE), a benchmark for scientific agents built from 113 tasks across 9 disciplines, written and reviewed by PhD students and postdocs from 34 institutions including Harvard, MIT and Stanford. Instead of Q&A, agents get real research goals and real tools (lab data, software, experiment videos) and are graded against hidden expert checks across six capabilities: hypothesis discovery, protocol planning, scientific computing, software operation, wet-lab readouts and experiment observation.
- The strongest configuration (Claude Opus 5 in Claude Code) scored just 37.5/100 on the composite leaderboard
- On the true end-to-end research track, every model scored 0
- Claude Opus 5.5 and GPT-6 Astra results are coming soon (clearing bio safeguards)
- Everything opens Nov 6
More from Models
- A Claude names itself "Mythos" and genders itself in a rare first-person exchange — repligate · 2026-11-06
- SemiAnalysis: Google TPUv7 Delivers Up to 50% Better Performance-per-Dollar Than B200/B300 for Inference — vllm_project · 2026-11-06
- World Labs launches Frameboy: real-time exploration of Atlas world model at up to 15 fps — theworldlabs · 2026-11-06
- Nested meme of dev posting 'HIT THE WEEKLY LIMIT OF CLAUDE AGAIN' every month — m3nt3_ · 2026-11-06
- FrontierPhysics benchmark: Claude Opus 5.5 tops end-to-end physics research at 27.4% — xeophon · 2026-11-06
- Why AI writing feels annoying despite models winning literary competitions — cis_female · 2026-11-06