Model comparison
MiMo-V2-Pro vs Qwen2-72B
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiMo-V2-Pro scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 40.8.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Qwen2-72B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 30.0 |
| Released | 2026-03-18 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 23 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Pro: 43.8 (#83), Qwen2-72B: 29.1 (#310)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1476 | 1196 |
| LMArena WebDev | 1433 | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 785.17 | — |
Agentic & Tool Use Not comparable
MiMo-V2-Pro: —, Qwen2-72B: 17.0 (#146)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
MiMo-V2-Pro: 22.1 (#206), Qwen2-72B: 23.2 (#181)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1191 |
| NYT Connections (extended) | 25.8% | — |
| Thematic Generalization | 45.9% | — |
| Epoch Capabilities Index | — | 125.28 |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 39.5 (#102), Qwen2-72B: 30.2 (#236)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1447 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge MiMo-V2-Pro leads
MiMo-V2-Pro: 41.4 (#111), Qwen2-72B: 21.2 (#275)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1478 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual MiMo-V2-Pro leads
MiMo-V2-Pro: 52.7 (#81), Qwen2-72B: 35.9 (#244)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1416 | 1176 |
| LMArena Chinese | 1456 | 1240 |
| LMArena French | 1469 | 1170 |
| LMArena German | 1417 | 1151 |
| LMArena Japanese | 1366 | 1111 |
| LMArena Korean | 1400 | 1083 |
| LMArena Russian | 1427 | 1169 |
| LMArena Spanish | 1457 | 1169 |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Pro: 76.0 (#49), Qwen2-72B: 61.7 (#241)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1445 | 1181 |
Long Context MiMo-V2-Pro leads
MiMo-V2-Pro: 41.5 (#138), Qwen2-72B: 36.1 (#235)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1455 | 1192 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
Writing & Preference MiMo-V2-Pro leads
MiMo-V2-Pro: 62.8 (#70), Qwen2-72B: 40.8 (#241)
| Benchmark | MiMo-V2-Pro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1436 | 1203 |
| LMArena Creative Writing | 1415 | 1181 |
| LMArena Multi-Turn | 1456 | 1196 |
Frequently asked questions
Is MiMo-V2-Pro better than Qwen2-72B?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 30.0 on the Noometry Index.
Is MiMo-V2-Pro or Qwen2-72B better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 29.1 in the Noometry coding category.
How many benchmarks do MiMo-V2-Pro and Qwen2-72B share?
17 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen2-72B has 26.