Model comparison
MiMo-V2.5 vs Qwen2-72B
MiMo-V2.5 is the stronger model overall, scoring 43.4 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-V2.5 scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 40.8.
Side by side
| MiMo-V2.5 | Qwen2-72B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 30.0 |
| Released | 2026-04-22 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 23 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Qwen2-72B: 29.1 (#310)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1469 | 1196 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 513.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Qwen2-72B: 17.0 (#146)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Qwen2-72B: 23.2 (#181)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1191 |
| CritPt | 3.7% | — |
| Epoch Capabilities Index | — | 125.28 |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Qwen2-72B: 30.2 (#236)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1436 | 1235 |
| ProofBench | 16% | — |
| MATH Level 5 | — | 39.1% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Qwen2-72B: 21.2 (#275)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1460 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen2-72B: —
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Qwen2-72B: 35.9 (#244)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1404 | 1176 |
| LMArena Chinese | 1468 | 1240 |
| LMArena French | 1447 | 1170 |
| LMArena German | 1421 | 1151 |
| LMArena Japanese | 1306 | 1111 |
| LMArena Korean | 1363 | 1083 |
| LMArena Russian | 1395 | 1169 |
| LMArena Spanish | 1416 | 1169 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Qwen2-72B: 61.7 (#241)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1181 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Qwen2-72B: 36.1 (#235)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1445 | 1192 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Qwen2-72B: 40.8 (#241)
| Benchmark | MiMo-V2.5 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1428 | 1203 |
| LMArena Creative Writing | 1393 | 1181 |
| LMArena Multi-Turn | 1445 | 1196 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen2-72B?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 30.0 on the Noometry Index.
Is MiMo-V2.5 or Qwen2-72B better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 29.1 in the Noometry coding category.
How many benchmarks do MiMo-V2.5 and Qwen2-72B share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen2-72B has 26.