Model comparison
MiMo-V2.5 vs Qwen Max
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 34.7 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 Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5 leads 36.8 to 22.3.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 33K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5 | Qwen Max | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 34.7 |
| Released | 2026-04-22 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 33K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.14 | $1.60 |
| Output $ / M tokens | $0.28 | $6.40 |
| Results tracked | 23 | 23 |
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), Qwen Max: 30.7 (#292)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Coding | 1469 | 1288 |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Qwen Max: 25.1 (#151)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1269 |
| CritPt | 3.7% | — |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Qwen Max: 22.3 (#276)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Math | 1436 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| ProofBench | 16% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Qwen Max: 30.3 (#228)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Expert | 1460 | 1248 |
| GPQA Diamond | — | 56.1% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen Max: —
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Qwen Max: 41.8 (#202)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1404 | 1263 |
| LMArena Chinese | 1468 | 1254 |
| LMArena French | 1447 | 1330 |
| LMArena German | 1421 | 1254 |
| LMArena Japanese | 1306 | 1205 |
| LMArena Korean | 1363 | 1142 |
| LMArena Russian | 1395 | 1274 |
| LMArena Spanish | 1416 | 1290 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Qwen Max: 66.5 (#208)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1434 | 1262 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Qwen Max: 39.4 (#180)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1445 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Qwen Max: 47.8 (#205)
| Benchmark | MiMo-V2.5 | Qwen Max |
|---|---|---|
| LMArena Text | 1428 | 1282 |
| LMArena Creative Writing | 1393 | 1248 |
| LMArena Multi-Turn | 1445 | 1277 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen Max?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 34.7 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Qwen Max?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is MiMo-V2.5 or Qwen Max better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 33K.
How many benchmarks do MiMo-V2.5 and Qwen Max share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen Max has 23.