Anthropic
Claude Opus 5.5 (Default Fallback)
ReasoningClosed weights
- Intelligence
- 53.6
- Rank 5 of 744 measured models
- Output speed
- 75.3 t/s
- Rank 237 of 403 measured models
- Price/1M
- $8
- Rank 603 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $1.82
- Rank 159 of 193 measured models
Claude Opus 5.5 (High, Default Fallback) scores 53.6 on the Artificial Analysis Intelligence Index, ranking 5th of 744 measured models. The closest models on this index are Claude Fable 5.1 (Default Fallback) (53.4), GPT-6 Astra (52.7), and Gemini 4 Argon (High) (52.6). At $8 per million tokens (3:1 input/output blended price), it is cheaper than Claude Fable 5.1 (Default Fallback) ($20) and GPT-6 Astra ($20), more expensive than Gemini 4 Argon (High) ($4). With an output speed of 75.3 t/s, it is faster than Claude Fable 5.1 (Default Fallback) (71.1 t/s) and GPT-6 Astra (43.9 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Fable 5.1 (Default Fallback)
Anthropic · $20 · 71.1 t/s
53.4−0.2$2071.1 t/sCompare - GPT-6 Astra
OpenAI · $20 · 43.9 t/s
52.7−0.9$2043.9 t/sCompare - Gemini 4 Argon (High)
Google · $4 · —
52.6−1.0$4—Compare - Muse Wonder (Max)
Meta · $8 · 131 t/s
52.4−1.2$8131 t/sCompare
