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

Claude Fable 5.2 (Max, Default Fallback) has achieved a score of 65 on the Artificial Analysis Intelligence Index, making it the highest scoring model so far. This model is known for its high intelligence level, though it comes with a higher price tag and slower processing speed compared to other models of similar cost. The model accepts both text and image inputs and generates text outputs, with a 1 million token context window.

The AI Index score of 65 places Claude Fable 5.2 well above the median of 40 for comparable models. During testing, the model generated 275 million tokens, which is significantly more verbose than the median of 72.8 million tokens for similar models. Pricing for this model is substantially higher than the median: $8.00 per 1 million input tokens and $40.00 per 1 million output tokens.

Evaluating Claude Fable 5.2 on the AI Index costs an average of $26.54 per task, which is notably slower than the median speed of 12.9 minutes for comparable models. The model's performance was measured against a set of other models, all using the Artificial Analysis Intelligence Index v5.0.1 as a benchmark.