- Intelligence
- 29.5
- Rank 131 of 744 measured models
- Coding
- 66.0
- Rank 68 of 298 measured models
- Output speed
- 191 t/s
- Rank 39 of 403 measured models
- Price/1M
- $3.75
- Rank 524 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $1.15
- Rank 140 of 193 measured models
Qwen3.7 Max scores 29.5 on the Artificial Analysis Intelligence Index, ranking 131st of 744 measured models. The closest models on this index are Gemini 3.1 Pro Preview (29.7), MiniMax-M3 (29.2), and Claude Opus 4.5 (batch) (29.1). At $3.75 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 3.1 Pro Preview ($4.50), more expensive than MiniMax-M3 ($0.525). With an output speed of 191 t/s, it is faster than Gemini 3.1 Pro Preview (131 t/s) and MiniMax-M3 (99.4 t/s).
Additional benchmarks16
Design Arena · 3d54.6%
Design Arena · Agenticgamedev46.6%
Design Arena · Androidnative48.9%
Design Arena · Asciiart53.2%
Design Arena · Codecategories54.1%
Design Arena · Dataviz52.9%
Design Arena · Fullstack47.7%
Design Arena · Gamedev53.4%
Design Arena · Godotgamedev55.7%
Design Arena · Htmlslides43.6%
Design Arena · Mobileapps44.9%
Design Arena · Python Pptxslides47.2%
Design Arena · Svg55.4%
Design Arena · Uicomponent53.4%
Design Arena · Webapps49.4%
Design Arena · Website54.5%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Sonnet 4.6 (batch)
Anthropic · — · —
30.1+0.6——Compare - Gemini 3.1 Pro Preview
Google · $4.50 · 131 t/s
29.7+0.2$4.50131 t/sCompare - MiniMax-M3
MiniMax · $0.525 · 99.4 t/s
29.2−0.3$0.52599.4 t/sCompare - Claude Opus 4.5 (batch)
Anthropic · — · —
29.1−0.4——Compare
