Qwen 3.8 Max vs 
MiMo V2.6 Pro
Both are SOTA right now. Each row is one board’s call, and the marked figure is the one that board places higher. No row is added to another, so there is no overall winner: the boards measure different things, and where they split, that is the finding.Each rank is the board’s own: the rank it publishes, or the model’s place in the board’s own order where it publishes none. Scores from different boards cannot be compared.
| Board | Qwen 3.8 Max | MiMo V2.6 Pro |
|---|---|---|
| Artificial Analysis LLM Leaderboard Artificial Analysis Intelligence Index | 45.4 No. 14 of 375 | 46.3 No. 13 of 375 |
| Arena — Agent Overall | 0.023 No. 23 of 52 | 0.035 No. 19 of 52 |
| Artificial Analysis Coding Agents Artificial Analysis Coding Agent Index | 0.433 No. 18 of 24 | — |
| Epoch AI Benchmarking Hub FrontierMath Tiers 1–3 | 74.7% No. 19 of 82 | — |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 27.0% No. 25 of 35 | — |
| Arena — Code Overall | 1674 No. 10 of 142 | 1629 No. 19 of 142 |
| Arena — Text Overall (style control) | 1483 No. 22 of 414 | 1480 No. 26 of 414 |
| Arena — Vision Overall (style control) | 1301 No. 2 of 165 | 1246 No. 59 of 165 |
At a glance
| Developer | Alibaba | Xiaomi |
|---|---|---|
| Weights | open | open |
| Released | 2026-08-03 | — |
| Price Blended Price, USD per 1M tokens (3:1 input:output) | $3.00 | $0.54 |
| Value: where it sits on the kill line | SOTA | SOTA |
Qwen 3.8 Max →MiMo V2.6 Pro → How the kill line is drawn →