CORE-Bench v1.1 (OpenCode): 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 OpenCode 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; OpenCode scaffold, reasoning as labeled; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (High) | 84.6 | #123 (GPT-5.4) |
| 2 | Claude Opus 4.6 (Non-reasoning) | 82.1 | #102 (Claude Opus 4.6) |
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-opencode · How It Works · Data refreshed daily, snapshot 2026-11-13.