Artificial Analysis ranks Claude Fable 5.2 #1 on AA-3D, its interactive 3D benchmark

Artificial Analysis says Claude Fable 5.2 (Max) is #1 on AA-3D, its benchmark for how well AI models build interactive 3D experiences, with 1271 Elo. That is 67 points ahead of Claude Sonnet 5.5 (1204) and Claude Opus 5.5 (1202); it says the 95% confidence interval (1246 to 1297) does not overlap any other model's.

It also reports Fable 5.2 132 points above Claude Fable 5.1 (1139), and ahead of the top OpenAI and Google models on the benchmark, GPT-6 Astra (1168) and Gemini 4 Argon (1147).

These are Artificial Analysis's own figures.