SignalTech/AI
Claude Fable 5.2 scores 65 on Artificial Analysis, highest so far
Claude Fable 5.2's 65 on Artificial Analysis is the highest score so far.
Context
What happened: Claude Fable 5.2 (Max, Default Fallback), released November 9, 2026 by Anthropic, scored 65 on the Artificial Analysis Intelligence Index, the highest score so far.
Key numbers: Score 65 vs median 40. $8.00 per 1M input tokens and $40.00 per 1M output tokens (medians: $2.00 and $10.00). $26.54 average cost per task. 275M output tokens generated vs median 72.8M. 1M token context window.
Why it matters: The model ranks among the leading models in intelligence, but the analysis describes it as particularly expensive compared to other models of similar price.
What changed
Claude Fable 5.2 (Max, Default Fallback), released November 9, 2026 by Anthropic, scored 65 on the Artificial Analysis Intelligence Index, the highest score so far.
Why it matters
The model ranks among the leading models in intelligence, but the analysis describes it as particularly expensive compared to other models of similar price.