- Intelligence
- 48.1
- Rank 25 of 749 measured models
- Coding
- 75.8
- Rank 26 of 298 measured models
- Output speed
- 144 t/s
- Rank 108 of 410 measured models
- Price/1M
- $2
- Rank 476 of 670 measured models
- Context window
- 1M
- Rank 86 of 1216 measured models
- Cost per task
- $1.60
- Rank 159 of 198 measured models
Muse Spark 1.3 (Max) scores 48.1 on the Artificial Analysis Intelligence Index, ranking 25th of 749 measured models. The closest models on this index are Claude Fable 5 (batch) (49.6), GPT-6 Sol (47.6), and GPT-5.6 Sol (47.0). At $2 per million tokens (3:1 input/output blended price), it is cheaper than GPT-6 Sol ($4) and GPT-5.6 Sol ($8). With an output speed of 144 t/s, it is faster than GPT-6 Sol (125 t/s) and GPT-5.6 Sol (88.5 t/s).
Additional benchmarks13
Design Arena · 3d63.5%
Design Arena · Asciiart53.9%
Design Arena · Codecategories57.3%
Design Arena · Dataviz58.1%
Design Arena · Fullstack60.8%
Design Arena · Gamedev56.0%
Design Arena · Godotgamedev45.8%
Design Arena · Mobileapps49.6%
Design Arena · Python Pptxslides51.4%
Design Arena · Svg54.0%
Design Arena · Uicomponent57.7%
Design Arena · Webapps54.8%
Design Arena · Website58.2%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Fable 5 (batch)
Anthropic · — · —
49.6+1.5——Compare - GPT-6 Sol
OpenAI · $4 · 125 t/s
47.6−0.5$4125 t/sCompare - GPT-5.6 Sol
OpenAI · $8 · 88.5 t/s
47.0−1.1$888.5 t/sCompare - Grok 4.7
SpaceXSI · $3 · 91.9 t/s
46.4−1.7$391.9 t/sCompare
