Claude Fable 5.2 (max) - Intelligence, Performance & Price Analysis | Artificial Analysis

Claude Fable 5.2 (Max, Default Fallback) scored 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models, but ranks among the most expensive options in its tier. The model accepts text and image inputs, outputs text, and carries a 1M-token context window. Pricing is $8.00 per 1M input tokens versus a $2.00 median and $40.00 per 1M output tokens versus a $10.00 median, with an average cost of $26.54 per task on the Intelligence Index. Its evaluation run consumed 275M tokens, far above the 72.8M median, reflecting unusually verbose output that compounds per-token costs. The results matter because they highlight a widening gap between capability and cost efficiency at the frontier, and watchers should track whether the model's verbosity and premium pricing hold up across real-world workloads rather than benchmark runs.