Science's Last Exam: Best of 8 frontier models scores 37.5/100, all zero on end-to-end research
geoffwolfe · x · 2026-11-07
Science's Last Exam (SLE), shared by Yang Ling, produced a striking result: across 113 scientific tasks, the best of eight frontier models scored just 37.5/100, and all eight scored zero on the end-to-end research task.
SLE has models pursue research objectives using computational tools, with final artifacts assessed against hidden, expert-defined checks. Its drug-regimen task, for example, requires balancing efficacy and safety across simulated conditions and establishing where conclusions hold. ReasonCoreAI notes this tests a key combination of scientific knowledge, experimental judgment, and validation of resulting work — real AI-driven scientific research remains far off.
More from Research
- DSReg: multi-lab preprint disentangles predictive representations without decoders — jiqizhixin · 2026-11-07
- New paper 'Inter-AI Morality' studies how AI systems treat one another — jacyanthis · 2026-11-07
- Steering one GQA key/value group makes a model claim "I am a user" 40 of 40 times — Sauers_ · 2026-11-07
- New research examines the economics of AI for science: winners and bottlenecks — Afinetheorem · 2026-11-07
- Sand3D Explorer lets you browse 106K+ 3D objects with parts, mechanisms and code — victormustar · 2026-11-07
- AI for bio is here: agent usage in Benchling surged through late 2026 — AllThingsApx · 2026-11-07