Tuesday, October 27, 2026i10X News · Section desk9 stories
Studies
Benchmarks & Evals
New benchmarks, evaluation methods and leaderboard results
FilterDeepSeek
Filtered: DeepSeek in Benchmarks & Evals · 2 storiesReset filter ×
-
Only One AI Agent Beats Researchers’ Own Code on Most FrontierCS 2 Tasks
FrontierCS 2 deletes a paper’s contribution from its repository and asks agents to beat the authors’ own code. Claude Opus 5.5 passes 58% of 48 tasks; every other agent passes under half, and 16 tasks stay unsolved.
By
Editor's picks
- Tampered ML: Even the Best AI Models Miss One in Five Planted Research Flaws
- Only One AI Agent Beats Researchers’ Own Code on Most FrontierCS 2 Tasks
- Hybrid Computer-Use Agents Top Out at 41% When GUI and CLI Must Work Together
- Scientific AI Agents Finish Only 21% of End-to-End Workflows — and Often Claim Success Anyway
- AI Agents Guess Wrong at Critical Forks 40% of the Time, Taste-Bench Shows
More stories
· RSS