Terminal-Bench Expands to Scientific Workflows
StanfordAILab · x · 2026-07-13
Stanford AI Lab announces Terminal-Bench Science, extending Terminal-Bench from coding tasks to evaluating AI agents on real scientific workflows.
The project is open for task contributions, aiming to systematically measure agent performance in scientific domains rather than just code problems.
More from coding & agent
- Hugging Face wraps 6-month Training Agents series with open recordings and code — SergioPaniego · 2026-10-26
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26