Artificial Analysis (@ArtificialAnlys)T1·基座大模型

Claude Fable 5.2 登顶 AA-3D 3D 交互榜

原标题：Claude Fable 5.2 is now #1 on AA-3D, our benchmark for how well AI models build interactive 3D exper...

58AI 研判分

Artificial Analysis 的 AA-3D 基准显示，Claude Fable 5.2 (Max) 以 1271 Elo 登顶，领先 Claude Sonnet 5.5 与 Opus 5.5 达 67 分，且置信区间与所有其他模型不重叠，领先幅度超出误差范围。它比前代 Fable 5.1 高出 132 分，并超过 OpenAI GPT-6 Astra（1168）与 Google Gemini 4 Argon（1147）。

关联知识实体

公司Anthropic 模型Gemini 4 Argon 术语AA-3D 模型GPT-6 Astra 模型Claude Fable 5.2 公司Artificial Analysis

报道正文

Artificial Analysis (@ArtificialAnlys) · 2026-11-10 00

Claude Fable 5.2 is now #1 on AA-3D, our benchmark for how well AI models build interactive 3D experiences

Claude Fable 5.2 (Max) scores 1271 Elo, 67 points ahead of Claude Sonnet 5.5 (1204) and Claude Opus 5.5 (1202). Its 95% confidence interval (1246 to 1297) does not overlap any other models, so its lead is outside the margin of error.

Key results:

➤ It scores 132 points above its predecessor, Claude Fable 5.1 (1139)

➤ It is ahead of the highest-ranked OpenAI and Google models on AA-3D, GPT-6 Astra (1168) and Gemini 4 Argon (1147)

More results and scenes in the thread below

推文配图