Arena 官方宣布 Claude Opus 5.5 (High) 进入 Agent Arena 排名第 2，净改进分 +12.15%，仅次于 Fable 5.1 (Max)。其中位价格为每任务 $1.31，比 Opus 5 (High) 便宜 40%、比 Opus 5 (Max) 便宜 56%，分项上 Steerability 排名第 1（+14.50%）。
Opus 5.5 (High) 在 Agent Arena 中排名第2，并重塑了帕累托前沿。Opus 5.5 (high) 不仅比两个 Opus 5 变体都有更高的净改进分数，而且成本还低了 40–56%：
- Opus 5.5 (High)：每任务中位数 $1.31 / 净改进 +12.15%
- Opus 5 (Max)：每任务中位数 $2.98 / 净改进 +9.58%
- Opus 5 (High)：每任务中位数 $2.17 / 净改进 +9.47%
再次祝贺 @AnthropicAI！
来自 @AnthropicAI 的 Claude Opus 5.5 (High) 刚刚进入 Agent Arena，排名第 #2，净提升分数为 +12.15%。只有 Fable 5.1 (Max) 排名更高。然而，Opus 5.5 (High) 每任务中位价格为 $1.31，成本降低了 64%，从而推进了帕累托前沿。 Opus 5.5 (High) 的净提升分数高于之前两个 Opus 5 变体，同时成本比 Opus 5 (High) 低 40%，比 Opus 5 (Max) 低 56%。 按信号划分，Opus 5.5 (High) 排名： - #1 可操控性 (+14.50%) - #2 确认成功 (+15.50%) - #3 表扬与投诉对比 (+19.80%) - #4 Bash 恢复 (+10.64%) 祝贺 @AnthropicAI 又发布了一款前沿模型！
原文
Claude Opus 5.5 (High) from @AnthropicAI just entered Agent Arena at #2, with a net improvement score of +12.15%. Only Fable 5.1 (Max) ranks higher. However, at a $1.31 median price per task, Opus 5.5 (High) comes in at 64% less cost, pushing out the Pareto frontier. Opus 5.5 (High) posts a higher net improvement score than both prior Opus 5 variants, while costing 40% less than Opus 5 (High) and 56% less than Opus 5 (Max). By signal, Opus 5.5 (High) ranks: - #1 Steerability (+14.50%) - #2 Confirmed Success (+15.50%) - #3 Praise vs Complaint (+19.80%) - #4 Bash Recovery (+10.64%) Congrats to the @AnthropicAI on another frontier model release!
来源：Arena.ai · x.com