Trending storyPast story
Claude Opus 5.5 tops Coding Agent Index, but per-task cost rises to $13.04
1 report1 sourceupdated 5 days ago
What happened
Summary
Artificial Analysis 把 Claude Opus 5.5 放在 Claude Code 的“最大出力”模式下跑了一遍 Coding Agent Index，得分 66，比上一代 Opus 5 的 60 分高出 6 分。三项子测试全线上涨：Terminal-Bench 4.0 正确率 63.1%，DeepSWE v1.1 正确率 68....
Coverage
Follow the reports to see the story from different sides.
Sep 24
- AI HOT (Curated Pool)PickClaude Opus 5.5 tops Coding Agent Index, but per-task cost rises to $13.04
Artificial Analysis tested Claude Opus 5.5 under Claude Code max effort and it scored 66 on the Coding Agent Index, up from Opus 5's 60. All three subtests improved: Terminal-Bench 4.0 63.1%, DeepSWE v1.1 68.4%, SWE-Atlas-QnA 66.4%. The trade-off: per-task cost jumped from $3 to $13.04. The post doesn't break down how max effort drove the cost increase.