CORE-Bench v1.1 (Codex CLI): 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; Codex CLI scaffold with default settings (subagents off), reasoning effort as labeled; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.

Top models

#ModelScore
1GPT-5.4 (High)97.4
2GPT-5.4 (xHigh)97.4
3GPT-5.2 (Medium)94.9
4GPT-5.4 (Medium)94.9
5GPT-5.4 (Low)92.3
6GPT-5.1 (Medium)87.2
7GPT-5 (Medium)84.6

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