- Intelligence
- 29.9
- Rank 131 of 781 measured models
- Output speed
- 57.1 t/s
- Rank 346 of 449 measured models
- Price/1M
- $0.544
- Rank 333 of 740 measured models
- Context window
- 1M
- Rank 107 of 1323 measured models
- Cost per task
- $0.257
- Rank 81 of 229 measured models
MiMo-V2.6-Pro scores 29.9 on the Artificial Analysis Intelligence Index, ranking 131st of 781 measured models. The closest models on this index are Claude Sonnet 4.6 (30.1), Gemini 3.1 Pro Preview (29.7), and Ling 3.1 Flash 1019 (29.6). At $0.544 per million tokens (3:1 input/output blended price), it is cheaper than Claude Sonnet 4.6 ($6) and Gemini 3.1 Pro Preview ($4.50), more expensive than Ling 3.1 Flash 1019 ($0.45). With an output speed of 57.1 t/s, it is faster than Claude Sonnet 4.6 (53.7 t/s), slower than Gemini 3.1 Pro Preview (112 t/s).
Additional benchmarks8
Design Arena · 3d57.4%
Design Arena · Codecategories52.5%
Design Arena · Dataviz58.7%
Design Arena · Gamedev52.9%
Design Arena · Svg55.7%
Design Arena · Uicomponent58.2%
Design Arena · Webapps58.2%
Design Arena · Website50.7%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Sonnet 4.6
Anthropic · $6 · 53.7 t/s
30.1+0.2$653.7 t/sCompare - Gemini 3.1 Pro Preview
Google · $4.50 · 112 t/s
29.7−0.2$4.50112 t/sCompare - Ling 3.1 Flash 1019
InclusionAI · $0.45 · —
29.6−0.3$0.45—Compare - Qwen3.7 Max
Alibaba · $3.75 · 158 t/s
29.5−0.4$3.75158 t/sCompare
