模型60

GitHub 发布 Copilot Fusion Max,Terminal-Bench 4.1 解决率 71.2%

原标题:🆕 On Terminal-Bench 4.1, Copilot Fusion Max achieved a 71.2% resolution rate, 5.4 percentage points ahead of leading frontier models Opu...

GitHub@github发布时间 (北京时间)

GitHub 发布 Copilot Fusion Max,在 Terminal-Bench 4.1 上解决率为 71.2%,比领先前沿模型 Opus 5.5 和 Fable 5.2 高出 5.4 个百分点。其成本比 Fable 5.2 低 88%,比 Opus 5.5 低 57%。

中文译文尚未完成,先为你展示原文。

🆕 On Terminal-Bench 4.1, Copilot Fusion Max achieved a 71.2% resolution rate, 5.4 percentage points ahead of leading frontier models Opus 5.5 and Fable 5.2, while costing 88% less than Fable 5.2 and 57% less than Opus 5.5.
https://docs.github.com/copilot/concepts/models/copilot-fusion?utm_source=x-fusion&utm_medium=social&utm_campaign=ignite-nov-2026

Microsoft / CopilotAI 编码部署工程评测基准#评测/基准#编码#部署/工程#GitHub#Microsoft