- Intelligence
- 52.4
- Rank 10 of 744 measured models
- Output speed
- 131 t/s
- Rank 115 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
- $4.52
- Rank 184 of 193 measured models
Muse Wonder (Max) scores 52.4 on the Artificial Analysis Intelligence Index, ranking 10th of 744 measured models. The closest models on this index are GPT-6 Astra (52.7), Gemini 4 Argon (High) (52.6), and GPT-6.1 Sol (51.8). At $8 per million tokens (3:1 input/output blended price), it is cheaper than GPT-6 Astra ($20), more expensive than Gemini 4 Argon (High) ($4) and GPT-6.1 Sol ($4). With an output speed of 131 t/s, it is faster than GPT-6 Astra (43.9 t/s) and GPT-6.1 Sol (47.9 t/s).
Additional benchmarks6
Design Arena · 3d68.6%
Design Arena · Codecategories62.7%
Design Arena · Dataviz61.4%
Design Arena · Gamedev62.8%
Design Arena · Uicomponent64.4%
Design Arena · Website62.0%
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+1.0$2071.1 t/sCompare - GPT-6 Astra
OpenAI · $20 · 43.9 t/s
52.7+0.3$2043.9 t/sCompare - Gemini 4 Argon (High)
Google · $4 · —
52.6+0.2$4—Compare - GPT-6.1 Sol
OpenAI · $4 · 47.9 t/s
51.8−0.6$447.9 t/sCompare
