Claude Fable 5.2 leads VIALS-AA benchmark with most tool calls
In this conversation · 1
10 NovClaude Fable 5.2 is now #1 on AA-3D, our benchmark for how well AI models build interactive 3D experiences
Artificial Analysis reports that Anthropic's Claude Fable 5.2 has reached the top of its AA-3D benchmark for AI models building interactive 3D experiences, scoring 1271 Elo. The model leads by 67 points over Claude Sonnet 5.5 and Claude Opus 5.5, with a 95% confidence interval that does not overlap any other model, making its lead statistically significant. Claude Fable 5.2 also outperforms the highest-ranked OpenAI and Google models on the benchmark, GPT-6 Astra and Gemini 4 Argon, according to
Artificial Analysis.
- Claude Fable 5.2 scored 1271 Elo, 67 points ahead of Claude Sonnet 5.5 (1204) and Claude Opus 5.5 (1202), with a 95% confidence interval of 1246 to 1297 that does not overlap any other model.
Artificial Analysis
- The model scored 132 points above its predecessor, Claude Fable 5.1 (1139).
Artificial Analysis
- Claude Fable 5.2 is ahead of the highest-ranked OpenAI and Google models on AA-3D: GPT-6 Astra (1168) and Gemini 4 Argon (1147).
Artificial Analysis
- Claude Fable 5.2 scored 1271 Elo, 67 points ahead of Claude Sonnet 5.5 (1204) and Claude Opus 5.5 (1202), with a 95% confidence interval of 1246 to 1297 that does not overlap any other model.


