Model comparison
MiMo-V2.5-Pro vs Qwen2.5-Max
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 40.1 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 Qwen2.5-Max 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 55.6.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | Qwen2.5-Max | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 44.8 | 40.1 |
| Released | 2026-04-22 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 27 |
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), Qwen2.5-Max: 41.2 (#118)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1502 | 1359 |
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 899.8 | — |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 25.9 (#124), Qwen2.5-Max: 24.6 (#144)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1487 | 1360 |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 84.5% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 38.6 (#84), Qwen2.5-Max: 34.3 (#162)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1480 | 1369 |
| ProofBench | 22% | — |
| LiveBench Math | — | 58.4% |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 41.5 (#100), Qwen2.5-Max: 34.8 (#181)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1501 | 1337 |
| Confabulations | — | 21.8% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.3 (#33), Qwen2.5-Max: 48.3 (#140)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1449 | 1352 |
| LMArena Chinese | 1507 | 1382 |
| LMArena French | 1489 | 1396 |
| LMArena German | 1455 | 1350 |
| LMArena Japanese | 1418 | 1299 |
| LMArena Korean | 1436 | 1304 |
| LMArena Russian | 1450 | 1353 |
| LMArena Spanish | 1470 | 1377 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.6 (#21), Qwen2.5-Max: 71.5 (#147)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1477 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#38), Qwen2.5-Max: 41.3 (#137)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1482 | 1358 |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.5 (#47), Qwen2.5-Max: 55.6 (#141)
| Benchmark | MiMo-V2.5-Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1465 | 1367 |
| LMArena Creative Writing | 1440 | 1339 |
| LMArena Multi-Turn | 1477 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen2.5-Max?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 40.1 on the Noometry Index.
Is MiMo-V2.5-Pro or Qwen2.5-Max better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 41.2 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and Qwen2.5-Max share?
17 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen2.5-Max has 27.