- Intelligence
- 25.2
- Rank 171 of 744 measured models
- Coding
- 55.9
- Rank 104 of 298 measured models
- Output speed
- 55.9 t/s
- Rank 297 of 403 measured models
- Price/1M
- $0.70
- Rank 328 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.217
- Rank 76 of 193 measured models
Qwen3.7 Plus scores 25.2 on the Artificial Analysis Intelligence Index, ranking 171st of 744 measured models. The closest models on this index are Hy3 (25.3), Grok 4.20 0309 (25.2), and MiMo-V2-Omni-0327 (25.1). At $0.70 per million tokens (3:1 input/output blended price), it is cheaper than Grok 4.20 0309 ($3), more expensive than Hy3 ($0.241). With an output speed of 55.9 t/s, it is slower than Hy3 (84 t/s).
Additional benchmarks8
Design Arena · 3d48.4%
Design Arena · Asciiart41.3%
Design Arena · Codecategories50.3%
Design Arena · Dataviz51.0%
Design Arena · Gamedev49.4%
Design Arena · Svg46.8%
Design Arena · Uicomponent49.3%
Design Arena · Website50.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Hy3
Tencent · $0.241 · 84 t/s
25.3+0.1$0.24184 t/sCompare - K2 Horizon MoVA 36B A4B
Institute of Foundation Models · — · —
25.3+0.1——Compare - Grok 4.20 0309
SpaceXSI · $3 · —
25.2$3—Compare - MiMo-V2-Omni-0327
Xiaomi · — · —
25.1−0.1——Compare
