- Intelligence
- 64.6
- Rank 1 of 781 measured models
- Output speed
- 95 t/s
- Rank 196 of 449 measured models
- Context window
- 1M
- Rank 107 of 1323 measured models
- Cost per task
- $26.54
- Rank 229 of 229 measured models
Claude Fable 5.2 (Max, Default Fallback) scores 64.6 on the Artificial Analysis Intelligence Index, ranking 1st of 781 measured models. The closest models on this index are Gemini 4 Carbon (60.0), Claude Opus 5.5 (Default Fallback) (59.1), and GPT-6 Astra (56.9). With an output speed of 95 t/s, it is faster than Gemini 4 Carbon (77.5 t/s) and GPT-6 Astra (37.9 t/s), slower than Claude Opus 5.5 (Default Fallback) (115 t/s).
Additional benchmarks7
Design Arena · 3d78.3%
Design Arena · Codecategories59.0%
Design Arena · Gamedev64.8%
Design Arena · Mobileapps67.4%
Design Arena · Pdf75.0%
Design Arena · Uicomponent57.1%
Design Arena · Website55.1%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Gemini 4 Carbon
Google · $8 · 77.5 t/s
60.0−4.6$877.5 t/sCompare - Claude Opus 5.5 (Default Fallback)
Anthropic · $8 · 115 t/s
59.1−5.5$8115 t/sCompare - GPT-6 Astra
OpenAI · $20 · 37.9 t/s
56.9−7.7$2037.9 t/sCompare - GPT-6.1 Sol
OpenAI · $4 · 55 t/s
54.6−10.0$455 t/sCompare
