Model comparison
MiMo-V2.5 vs Qwen1.5-72B
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 30.8 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 Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2.5 leads 40.8 to 11.5.
Side by side
| MiMo-V2.5 | Qwen1.5-72B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 30.8 |
| Released | 2026-04-22 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 23 | 22 |
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), Qwen1.5-72B: 31.9 (#277)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1469 | 1165 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 513.95 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Qwen1.5-72B: 22.2 (#203)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1148 |
| CritPt | 3.7% | — |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Qwen1.5-72B: 33.2 (#205)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1436 | 1164 |
| ProofBench | 16% | — |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Qwen1.5-72B: 11.5 (#300)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1460 | 1136 |
| GPQA Diamond | — | 28.8% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen1.5-72B: —
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Qwen1.5-72B: 33.2 (#253)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1404 | 1135 |
| LMArena Chinese | 1468 | 1186 |
| LMArena French | 1447 | 1159 |
| LMArena German | 1421 | 1084 |
| LMArena Japanese | 1306 | 1061 |
| LMArena Korean | 1363 | 1050 |
| LMArena Russian | 1395 | 1104 |
| LMArena Spanish | 1416 | 1110 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Qwen1.5-72B: 59.3 (#256)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1141 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Qwen1.5-72B: 35.1 (#243)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1445 | 1157 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Qwen1.5-72B: 37.3 (#258)
| Benchmark | MiMo-V2.5 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1428 | 1166 |
| LMArena Creative Writing | 1393 | 1137 |
| LMArena Multi-Turn | 1445 | 1160 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen1.5-72B?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 30.8 on the Noometry Index.
Is MiMo-V2.5 or Qwen1.5-72B better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 31.9 in the Noometry coding category.
How many benchmarks do MiMo-V2.5 and Qwen1.5-72B share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen1.5-72B has 22.