Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far

Claude Fable 5.2 achieved a score of 65 on the Artificial Analysis Intelligence Index, ranking it as the highest-performing model in its class, significantly above the median score of 40. However, the model is notably expensive at $8.00 per million input tokens and $40.00 per million output tokens, and operates slowly at 45 minutes per task compared to the median of 12.9 minutes. The model also generates exceptionally verbose outputs, producing 275 million tokens during evaluation compared to the typical median of 72.8 million tokens.