- Intelligence
- 39.6
- Rank 56 of 768 measured models
- Coding
- 72.2
- Rank 40 of 299 measured models
- Output speed
- 233 t/s
- Rank 25 of 425 measured models
- Price/1M
- $2
- Rank 506 of 726 measured models
- Context window
- 1M
- Rank 90 of 1296 measured models
- Cost per task
- $0.812
- Rank 133 of 218 measured models
Muse Spark 1.2 (Xhigh) scores 39.6 on the Artificial Analysis Intelligence Index, ranking 56th of 768 measured models. The closest models on this index are Qwen3.8 2.4T A95B (39.9), Qwen3.8-Flash-Next (39.8), and Gemini 3.7 Flash (39.6). At $2 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.8 2.4T A95B ($3), more expensive than Qwen3.8-Flash-Next ($0.23) and Gemini 3.7 Flash ($1.50). With an output speed of 233 t/s, it is faster than Qwen3.8 2.4T A95B (37.8 t/s) and Qwen3.8-Flash-Next (51.9 t/s), slower than Gemini 3.7 Flash (383 t/s).
Additional benchmarks18
Design Arena · 3d51.9%
Design Arena · Agenticgamedev42.9%
Design Arena · Androidnative53.2%
Design Arena · Asciiart55.2%
Design Arena · Blender3d42.9%
Design Arena · Codecategories52.1%
Design Arena · Dataviz56.6%
Design Arena · Fullstack48.0%
Design Arena · Gamedev50.4%
Design Arena · Htmlslides40.0%
Design Arena · Mobileapps48.1%
Design Arena · Pdf37.1%
Design Arena · Python Pptxslides48.3%
Design Arena · Spreadsheet44.8%
Design Arena · Svg54.3%
Design Arena · Uicomponent52.2%
Design Arena · Webapps49.8%
Design Arena · Website52.2%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Qwen3.8 Max
Alibaba · $3 · 38.5 t/s
40.2+0.6$338.5 t/sCompare - Qwen3.8 2.4T A95B
Alibaba · $3 · 37.8 t/s
39.9+0.3$337.8 t/sCompare - Qwen3.8-Flash-Next
Alibaba · $0.23 · 51.9 t/s
39.8+0.2$0.2351.9 t/sCompare - Gemini 3.7 Flash
Google · $1.50 · 383 t/s
39.6$1.50383 t/sCompare
