Anthropic
Claude Fable 5.1 (Default Fallback)
ReasoningClosed weights
- Intelligence
- 53.2
- Rank 7 of 749 measured models
- Coding
- 80.7
- Rank 2 of 298 measured models
- Output speed
- 63.7 t/s
- Rank 296 of 410 measured models
- Price/1M
- $20
- Rank 650 of 671 measured models
- Context window
- 1M
- Rank 86 of 1216 measured models
- Cost per task
- $5.98
- Rank 195 of 198 measured models
Claude Fable 5.1 (Xhigh, Default Fallback) scores 53.2 on the Artificial Analysis Intelligence Index, ranking 7th of 749 measured models. The closest models on this index are GPT-6 Astra (52.7), Gemini 4 Argon (High) (52.6), and Muse Wonder (Max) (52.4). At $20 per million tokens (3:1 input/output blended price), it is priced close to GPT-6 Astra ($20), more expensive than Gemini 4 Argon (High) ($4) and Muse Wonder (Max) ($8). With an output speed of 63.7 t/s, it is slower than GPT-6 Astra (69.3 t/s), Gemini 4 Argon (High) (99.5 t/s), and Muse Wonder (Max) (176 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-6 Astra
OpenAI · $20 · 69.3 t/s
52.7−0.5$2069.3 t/sCompare - Gemini 4 Argon (High)
Google · $4 · 99.5 t/s
52.6−0.6$499.5 t/sCompare - Muse Wonder (Max)
Meta · $8 · 176 t/s
52.4−0.8$8176 t/sCompare - GPT-6.1 Sol
OpenAI · $4 · 59.8 t/s
51.8−1.4$459.8 t/sCompare
