Model comparison
MiMo-V2.6-Pro vs Qwen3.7 Plus
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 45.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Qwen3.7 Plus in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 36.6.
- The biggest single-benchmark swing is CritPt: 26.6% for MiMo-V2.6-Pro and 9.1% for Qwen3.7 Plus.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.6-Pro | Qwen3.7 Plus | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 45.3 |
| Released | 2026-09-21 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.43 | $0.40 |
| Output $ / M tokens | $0.87 | $1.60 |
| Results tracked | 19 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| SciCode | 60.9% | 45.5% |
| LMArena Coding | 1534 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1629 | — |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 59.5% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| CritPt | 26.6% | 9.1% |
| LMArena Hard Prompts | 1512 | 1460 |
| NYT Connections (extended) | — | 74.8% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.37 |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1494 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | 70% | — |
Knowledge Qwen3.7 Plus leads
MiMo-V2.6-Pro: 43.5 (#92), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1543 | 1467 |
| GPQA Diamond | — | 87.9% |
Multimodal Too close to call
MiMo-V2.6-Pro: 40.8 (#43), Qwen3.7 Plus: 41.8 (#33)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1264 | 1279 |
| LMArena Document | — | 1444 |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1474 | 1445 |
| LMArena Chinese | 1529 | 1510 |
| LMArena Russian | 1480 | 1457 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Spanish | — | 1457 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1493 | 1440 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1501 | 1455 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | MiMo-V2.6-Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1492 | 1455 |
| LMArena Creative Writing | 1468 | 1439 |
| LMArena Multi-Turn | 1464 | 1460 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Qwen3.7 Plus?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 45.3 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Pro or Qwen3.7 Plus?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is MiMo-V2.6-Pro or Qwen3.7 Plus better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 1M.
How many benchmarks do MiMo-V2.6-Pro and Qwen3.7 Plus share?
15 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen3.7 Plus has 32.