Model comparison
MiMo-V2.6-Pro vs Qwen2-72B
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.0 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 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 29.1.
Side by side
| MiMo-V2.6-Pro | Qwen2-72B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 30.0 |
| Released | 2026-09-21 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 19 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1534 | 1196 |
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Qwen2-72B: 17.0 (#146)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| APEX-Agents | 59.5% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Qwen2-72B: 23.2 (#181)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1512 | 1191 |
| CritPt | 26.6% | — |
| Epoch Capabilities Index | — | 125.28 |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Qwen2-72B: 30.2 (#236)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1494 | 1235 |
| ProofBench | 70% | — |
| MATH Level 5 | — | 39.1% |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Qwen2-72B: 21.2 (#275)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1543 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Qwen2-72B: —
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Qwen2-72B: 35.9 (#244)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1474 | 1176 |
| LMArena Chinese | 1529 | 1240 |
| LMArena Russian | 1480 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Qwen2-72B: 61.7 (#241)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1493 | 1181 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Qwen2-72B: 36.1 (#235)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1501 | 1192 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Qwen2-72B: 40.8 (#241)
| Benchmark | MiMo-V2.6-Pro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1492 | 1203 |
| LMArena Creative Writing | 1468 | 1181 |
| LMArena Multi-Turn | 1464 | 1196 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Qwen2-72B?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.0 on the Noometry Index.
Is MiMo-V2.6-Pro or Qwen2-72B better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 29.1 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Pro and Qwen2-72B share?
12 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen2-72B has 26.