CooperBench: leaderboard
Metric: Cooperative task success (%; two agents that can message each other each implement one feature of a task pair in isolated workspaces, and the merged patch must pass both features' tests after the naive, union and learned-resolver merge stages; 652 tasks). Source: arxiv.org. Saturation forecast: Around October 2027. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 27.9 |
| 2 | Claude Sonnet 4.5 | 25.92 |
| 3 | MiniMax-M2 | 13.96 |
| 4 | Qwen 3 Coder 30B A3B Instruct | 13.34 |
| 5 | Qwen 3 30B A3B 2507 Instruct | 4.6 |
Interactive version: theaggregate.ai/benchmark?slug=cooperbench · How It Works · Data refreshed daily, snapshot 2026-09-26.