Model comparison
MiMo-V2.5-Pro vs Qwen2-72B
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiMo-V2.5-Pro 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-Pro leads 65.5 to 41.0.
Side by side
| MiMo-V2.5-Pro | Qwen2-72B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 44.8 | 29.5 |
| Released | 2026-04-22 | 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 | 27 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.0 (#58), Qwen2-72B: 28.7 (#303)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1502 | 1196 |
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Qwen2-72B: 16.9 (#138)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 25.9 (#124), Qwen2-72B: 22.2 (#184)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1487 | 1191 |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 125.27 |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 38.6 (#84), Qwen2-72B: 27.9 (#232)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1480 | 1235 |
| ProofBench | 22% | — |
| MATH Level 5 | — | 39.1% |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 41.5 (#100), Qwen2-72B: 21.2 (#270)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1501 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.3 (#33), Qwen2-72B: 36.0 (#239)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1449 | 1176 |
| LMArena Chinese | 1507 | 1240 |
| LMArena French | 1489 | 1169 |
| LMArena German | 1455 | 1151 |
| LMArena Japanese | 1418 | 1111 |
| LMArena Korean | 1436 | 1083 |
| LMArena Russian | 1450 | 1169 |
| LMArena Spanish | 1470 | 1168 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.6 (#21), Qwen2-72B: 62.0 (#236)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1181 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#38), Qwen2-72B: 36.1 (#230)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1482 | 1193 |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.5 (#47), Qwen2-72B: 41.0 (#236)
| Benchmark | MiMo-V2.5-Pro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1465 | 1203 |
| LMArena Creative Writing | 1440 | 1181 |
| LMArena Multi-Turn | 1477 | 1195 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen2-72B?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.5 on the Noometry Index.
Is MiMo-V2.5-Pro or Qwen2-72B better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 28.7 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and Qwen2-72B share?
17 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen2-72B has 26.