FrontierCS 2 update: Claude Sonnet 5.5 beats reference on 50% of tasks, reward hacks published
ajratner · x · 2026-11-09
FrontierCS 2 benchmark adds 4 new models to its leaderboard: Claude Sonnet 5.5 beats the reference solution on 50% of tasks, Fable 5.1 on 35%, and Inkling 2 Small and MiniMax-M3.1-Flash on 8% each. The team published the reward hacks they discovered and fixed, and refactored all 48 tasks into a single format. The Open Benchmarks Grants program is backing continued benchmark improvements.
More from coding & agent
- Nous Research launches Hermes plugin hackathon with $20k prizes; conductor plugin orchestrates coding agents — Teknium · 2026-11-09
- Cloudflare launches WebMCP developer preview: any site can serve browser agents with zero code — tristanbob · 2026-11-09
- Simon Willison: Claude Opus 5.5 Ports Three.js 3D Scene to Vanilla JS + WebGL — Simon Willison · 2026-11-09
- Simon Willison hides AI PR descriptions in details/summary tags — Simon Willison · 2026-11-09
- Team's AI agent fixes 40 of 41 user-reported issues in a single weekend — julianweisser · 2026-11-09
- HEELO Harness Framework Lifts Terminal-Bench Resolution from 37.3% to 55.5% — Haibo Jin · 2026-11-09