Model comparison
MiMo-V2.5-Pro vs QwQ-32B
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 39.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 50.6.
Side by side
| MiMo-V2.5-Pro | QwQ-32B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 45.2 | 39.8 |
| Released | 2026-04-22 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 36 |
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: 47.4 (#60), QwQ-32B: 35.4 (#226)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Coding | 1503 | 1333 |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1479 | — |
| SciCode | 50.2% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 899.8 | — |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), QwQ-32B: 23.7 (#174)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1488 | 1325 |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 84.5% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 40.0 (#96), QwQ-32B: 38.0 (#143)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Math | 1481 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| ProofBench | 22% | — |
| LiveBench Math | — | 77.8% |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 42.2 (#98), QwQ-32B: 37.2 (#158)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Expert | 1503 | 1324 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.1 (#34), QwQ-32B: 44.8 (#176)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1449 | 1305 |
| LMArena Chinese | 1507 | 1378 |
| LMArena French | 1488 | 1336 |
| LMArena German | 1458 | 1313 |
| LMArena Japanese | 1412 | 1262 |
| LMArena Korean | 1437 | 1279 |
| LMArena Russian | 1450 | 1297 |
| LMArena Spanish | 1471 | 1354 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), QwQ-32B: 72.6 (#137)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
MiMo-V2.5-Pro: 45.4 (#37), QwQ-32B: 49.0 (#11)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1483 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.3 (#49), QwQ-32B: 50.6 (#180)
| Benchmark | MiMo-V2.5-Pro | QwQ-32B |
|---|---|---|
| LMArena Text | 1465 | 1329 |
| LMArena Creative Writing | 1440 | 1288 |
| EQ-Bench Creative Writing | 1493 | 1257 |
| LMArena Multi-Turn | 1477 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench 4 | 1208 | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is MiMo-V2.5-Pro better than QwQ-32B?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 39.8 on the Noometry Index.
Is MiMo-V2.5-Pro or QwQ-32B better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 35.4 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and QwQ-32B share?
18 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and QwQ-32B has 36.