Large Language Models
1d ago
Claude Fable 5.2 Achieves High Score on Intelligence Index but Comes with High Costs
Nov 9, 2026
AI Summary
Claude Fable 5.2, released in November 2026, scored 65 on the Artificial Analysis Intelligence Index, significantly above the median score of 40. However, it is noted for its high pricing and slower performance compared to similar models, with a cost of $8.00 per million input tokens and $40.00 per million output tokens.
- Claude Fable 5.2 (Max, Default Fallback) was released on November 9, 2026, by Anthropic.
- It scored 65 on the Artificial Analysis Intelligence Index, which is above the median score of 40 for comparable models.
- The model generated 275 million tokens during the evaluation, significantly higher than the median of 72.8 million tokens.
- It has a context window of 1 million tokens and supports both text and image input, producing text output.
- The model takes an average of 44.1 minutes per task on the Intelligence Index, which is slower than the median of 12.9 minutes for similar models.
- The cost for using Claude Fable 5.2 is $8.00 per million input tokens and $40.00 per million output tokens, which is higher than the median costs of $2.00 and $10.00 respectively.
- The average cost per task to evaluate the model is approximately $26.54.
- Claude Fable 5.2 is classified as a reasoning model, utilizing extended thinking processes to address complex problems.
claude fablelanguage modelartificial intelligenceperformanceai research