Event ·Multi-source

Claude Fable 5.1 (Max)登顶Agent Arena榜首

Claude Fable 5.1 (Max)在Agent Arena排行榜中位列第一，净性能提升达15.8%。该模型基于6.7万+真实智能体会话测试，每任务中位成本为4.14美元。用户情感反馈显示，其表扬率比投诉率高42.5%，是第二名模型的2倍。

Current read

Anthropic的Claude Fable 5.1 (Max)在Agent Arena排名第一，性能领先但成本较高，用户满意度极高。

11 sources78° AI heatLast updated 2026/9/6 01:02:47

Evidence

11 sources

Primary sourcelmarena.ai

2026/9/6 01:02:47View source

Related source 1IT之家

2026/9/4 23:20:46View source

Related source 2shao__meng

2026/9/7 06:38:22View source

Related source 3小互

2026/9/4 14:03:36View source

Related source 4arXiv: OpenAI

2026/9/4 14:57:17View source

Related source 5量子位

2026/9/5 01:17:56View source

Related source 6SuperTechFans

2026/9/5 23:35:52View source

Related source 7Gary Marcus

2026/9/6 13:46:01View source

Related source 8DeepLearning.AI

2026/9/4 17:38:47View source

Related source 9宝玉

2026/9/5 21:36:34View source

Related source 10AI Will

2026/9/7 02:47:57View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story