Fable 5.2 tops the AI leaderboard at 65, and costs double to run
Anthropic's Fable 5.2 is #1 on Artificial Analysis' index at 65, but at max effort a task costs about $26.50, double what Fable 5.1 cost.
Claude Fable 5.2 is now the highest-scoring model on the Artificial Analysis Intelligence Index v5. At max effort it scores 65. That puts it 5 points ahead of Gemini 4 Carbon (60), 6 ahead of Opus 5.5 (59) and 15 ahead of Fable 5.1.
The top score is expensive. At max effort an index task costs about $26.50. That is roughly double Fable 5.1 ($12.99) and about 2.6x Opus 5.5 ($10). The cost comes from how many tokens it uses, even though Anthropic cut list prices to $8/$40 per million input/output tokens. The cheaper settings are where it pays off. At High effort Fable 5.2 still scores 62, above Opus 5.5 at max, and uses about 98k output tokens per task to Opus's 173k.
It does not lead everywhere. In agentic knowledge work (AA-Briefcase) it sits just behind Sonnet 5.5. On Terminal-Bench 4.0 it ties Opus 5.5 at 60%, while Kimi K3.1 Pro and Gemini 4 Carbon score higher. Anthropic released it alongside Mythos 5.2, a cyber-focused model available only to verified organizations.
Why it matters: the top score now costs double, so for most workloads Fable 5.2 at High effort, not Max, is the version worth paying for.
Sources
Independent coverage
- Claude Fable 5.2 vs Claude Opus 5.5 - Intelligence, Performance & Price Comparison artificialanalysis.ai
- Claude Fable 5.2 and Mythos 5.2 cement Anthropic's AI lead just before its IPO the-decoder.com
Written by an AI pipeline from the sources above. Methodology · Report an error
The stories that matter for people who build with AI, with the source for every claim. Free, no spam.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.