Model comparison
MiMo-V2.5 vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 21× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiMo-V2.5 scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 36.8.
- The biggest single-benchmark swing is ProofBench: 16% for MiMo-V2.5 and 26% for Qwen3.7 Max.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5 | Qwen3.7 Max | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 51.5 |
| Released | 2026-04-22 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.14 | $2.50 |
| Output $ / M tokens | $0.28 | $7.50 |
| Results tracked | 23 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
MiMo-V2.5: 43.9 (#81), Qwen3.7 Max: 50.4 (#45)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1438 | 1515 |
| SciCode | 43.1% | 48.8% |
| LMArena Coding | 1469 | 1498 |
| ALE-Bench | 513.95 | 1,189 |
| SWE-bench Verified | — | 77.3% |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Qwen3.7 Max: 22.1 (#135)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
MiMo-V2.5: 28.6 (#101), Qwen3.7 Max: 49.2 (#38)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| CritPt | 3.7% | 13.4% |
| LMArena Hard Prompts | 1450 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.68 |
Math Qwen3.7 Max leads
MiMo-V2.5: 36.8 (#163), Qwen3.7 Max: 62.4 (#32)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| ProofBench | 16% | 26% |
| LMArena Math | 1436 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
Knowledge Qwen3.7 Max leads
MiMo-V2.5: 40.8 (#115), Qwen3.7 Max: 61.6 (#28)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1460 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen3.7 Max: —
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual Qwen3.7 Max leads
MiMo-V2.5: 51.9 (#99), Qwen3.7 Max: 56.9 (#15)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1404 | 1474 |
| LMArena Chinese | 1468 | 1530 |
| LMArena Russian | 1395 | 1484 |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
| LMArena Spanish | 1416 | — |
Instruction Following Qwen3.7 Max leads
MiMo-V2.5: 75.5 (#60), Qwen3.7 Max: 76.7 (#38)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1434 | 1460 |
Long Context Qwen3.7 Max leads
MiMo-V2.5: 44.2 (#73), Qwen3.7 Max: 45.4 (#40)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1445 | 1482 |
Writing & Preference Qwen3.7 Max leads
MiMo-V2.5: 61.6 (#86), Qwen3.7 Max: 65.0 (#54)
| Benchmark | MiMo-V2.5 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1428 | 1476 |
| LMArena Creative Writing | 1393 | 1449 |
| LMArena Multi-Turn | 1445 | 1481 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 21× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5 or Qwen3.7 Max?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is MiMo-V2.5 or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 1M.
How many benchmarks do MiMo-V2.5 and Qwen3.7 Max share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3.7 Max has 33.