CORE-Bench v1.1 (Codex CLI): leaderboard
CORE-Bench v1.1 (2026) is CORE-Bench Hard with 15 task errors and 20 shortcut tasks fixed and 10 new tasks: 39 tasks in which an agent reproduces the computational results of a paper from its code capsule and answers questions about them. This board is task accuracy in percent with the Codex CLI scaffold; higher is better.
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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (High) | 97.4 | #123 (GPT-5.4) |
| 2 | GPT-5.4 (xHigh) | 97.4 | #123 (GPT-5.4) |
| 3 | GPT-5.3 Codex (Medium) | 97.4 | #116 (GPT-5.3 Codex) |
| 4 | GPT-5.2 (Medium) | 94.9 | #176 (GPT-5.2) |
| 5 | GPT-5.4 (Medium) | 94.9 | #123 (GPT-5.4) |
| 6 | GPT-5.4 (Low) | 92.3 | #123 (GPT-5.4) |
| 7 | GPT-5.1 (Medium) | 87.2 | #229 (GPT-5.1) |
| 8 | GPT-5 (Medium) | 84.6 | #167 (GPT-5) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=core-bench-v1-1-codex-cli · How It Works · Data refreshed daily, snapshot 2026-11-13.