Model comparison
MiMo-V2.6-Pro vs Qwen1.5-32B
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.8 to 34.2.
Side by side
| MiMo-V2.6-Pro | Qwen1.5-32B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 30.5 |
| Released | 2026-09-21 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 19 | 21 |
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), Qwen1.5-32B: 31.7 (#282)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1534 | 1155 |
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use Not comparable
MiMo-V2.6-Pro: 37.5 (#35), Qwen1.5-32B: —
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| APEX-Agents | 59.5% | — |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Qwen1.5-32B: 21.8 (#212)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1512 | 1130 |
| CritPt | 26.6% | — |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Qwen1.5-32B: 33.0 (#207)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1494 | 1155 |
| ProofBench | 70% | — |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Qwen1.5-32B: 13.5 (#296)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1543 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Qwen1.5-32B: —
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Qwen1.5-32B: 31.4 (#259)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1474 | 1106 |
| LMArena Chinese | 1529 | 1177 |
| LMArena Russian | 1480 | 1073 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Spanish | — | 1089 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Qwen1.5-32B: 57.7 (#265)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1493 | 1116 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Qwen1.5-32B: 34.7 (#246)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1501 | 1146 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Qwen1.5-32B: 34.2 (#271)
| Benchmark | MiMo-V2.6-Pro | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1492 | 1137 |
| LMArena Creative Writing | 1468 | 1083 |
| LMArena Multi-Turn | 1464 | 1140 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Qwen1.5-32B?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.5 on the Noometry Index.
Is MiMo-V2.6-Pro or Qwen1.5-32B better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 31.7 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Pro and Qwen1.5-32B share?
12 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen1.5-32B has 21.