Claude Fable 5.2 scores 65 on Artificial Analysis, highest so far
Original title: Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far
Artificial Analysis Intelligence Index v5.0.1 rates Claude Fable 5.2 at 65, and the model has no public API.
Artificial Analysis lists Claude Fable 5.2 at 65 on Intelligence Index v5.0.1, the highest score shown so far. The index averages nine evaluations, including AA-Briefcase v1.1, Terminal-Bench 4.0, FrontierCode 2.0, HLE-Diamond, and CritPt v2. The page marks the model as having no publicly available API and also reports cost, token use, and capability indexes.
Unconfirmed: The score is Artificial Analysis's own measurement; the excerpt does not state who released the model or when.
- Index v5.0.1 uses nine evaluations, including Terminal-Bench-Science 0.1 and AA-Omniscience v1.1.
- The page repeatedly states there is no publicly available API.
- AA-Omniscience net scores range from -100 to 100 and penalize hallucinations.
- Cost per task is a weighted average of input, cache, reasoning, and answer token prices.
- Organizations
- Artificial Analysis
- AI models
- Claude Fable 5.2
From the original article
5 min read at artificialanalysis.aiArtificial Analysis Intelligence Index v5. 0. 1 incorporates 9 evaluations: AA-Briefcase v1.
By theanonymousone · artificialanalysis.ai
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.