Claude Fable 5.2 tops Artificial Analysis Intelligence Index v5

1. 2:45 PM
   Artificial Analysis@ArtificialAnlysOfficial

   Artificial Analysis says Claude Fable 5.2 leads 5 of 9 Intelligence Index v5 evaluations

   AIArtificial Analysis reports that Claude Fable 5.2 leads five of the nine evaluations in Intelligence Index v5, spanning science, knowledge and coding. It scores 80% on HLE-Diamond, 11 points ahead of Gemini 4 Carbon, and 67 on AA-Omniscience v1.1, 13 points ahead of Gemini 4 Carbon. The post also reports 73% on Terminal-Bench-Science and 49% on FrontierCode 2.0, a private code evaluation by Cognition.

   
2. 2:45 PM
   Artificial Analysis@ArtificialAnlysOfficial

   Artificial Analysis ranks Claude Fable 5.2 top on Intelligence Index

   AIArtificial Analysis says Claude Fable 5.2's high, xhigh and max settings are the three highest-scoring entries on its Intelligence Index. At high effort, Claude Fable 5.2 scores 62, ahead of Gemini 4 Carbon (high, 60) and Opus 5.5 (max, 59), using about 40% fewer output tokens than Opus 5.5 (max). At low effort, it beats Claude Fable 5.1 (max) by 5 points with about 70% fewer output tokens.

   
3. 2:45 PM
   Artificial Analysis@ArtificialAnlysOfficialPick

   Claude Fable 5.2 tops the Artificial Analysis Intelligence Index at 65

   AIArtificial Analysis says Anthropic's Claude Fable 5.2 ranks first on its Intelligence Index v5 with a score of 65, five points ahead of Gemini 4 Carbon at high effort. The source says the gains come mainly from scientific reasoning, knowledge and FrontierCode 2.0, while agentic and terminal coding tasks roughly match Claude Opus 5.5. At max effort the average cost per task is $26.5, about 2.6x Opus 5.5.

   

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.