CORE-Bench v1.1 (Claude Code): leaderboard

Metric: Task accuracy (%) on the 39 CORE-Bench v1.1 tasks (CORE-Bench Hard with 15 task errors and 20 shortcut tasks fixed plus 10 new tasks): reproduce a paper's computational results from its code capsule given only the README, code and data, and answer the task questions; Claude Code scaffold, thinking as labeled (10K-token budget for Opus 4.5, adaptive for Opus 4.6); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 2 models tracked.

Top models

#ModelScore
1Claude Opus 4.5 (Thinking)89.7

Interactive version: theaggregate.ai/benchmark?slug=core-bench-v1-1-claude-code · How It Works · Data refreshed daily, snapshot 2026-09-29.