Model comparison
MiMo-V2.5 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 17× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. MiMo-V2.5 scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 36.8.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 51.5 |
| Released | 2026-04-22 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.14 | $1.30 |
| Output $ / M tokens | $0.28 | $7.80 |
| Results tracked | 23 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
MiMo-V2.5: 43.9 (#81), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1438 | 1482 |
| LMArena Coding | 1469 | 1471 |
| SWE-bench Verified | — | 76.7% |
| SciCode | 43.1% | — |
| ALE-Bench | 513.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Qwen3.6 Max Preview: —
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
MiMo-V2.5: 28.6 (#101), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1457 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 3.7% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.24 |
Math Qwen3.6 Max Preview leads
MiMo-V2.5: 36.8 (#163), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1436 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| ProofBench | 16% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
MiMo-V2.5: 40.8 (#115), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1460 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Qwen3.6 Max Preview: —
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual Qwen3.6 Max Preview leads
MiMo-V2.5: 51.9 (#99), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1404 | 1437 |
| LMArena Chinese | 1468 | 1487 |
| LMArena French | 1447 | 1449 |
| LMArena Russian | 1395 | 1445 |
| LMArena Spanish | 1416 | 1454 |
| LMArena German | 1421 | — |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
Instruction Following Too close to call
MiMo-V2.5: 75.5 (#60), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1434 | 1438 |
Long Context Too close to call
MiMo-V2.5: 44.2 (#73), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1445 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
MiMo-V2.5: 61.6 (#86), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | MiMo-V2.5 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1428 | 1447 |
| LMArena Creative Writing | 1393 | 1435 |
| LMArena Multi-Turn | 1445 | 1456 |
Frequently asked questions
Is MiMo-V2.5 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 17× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5 or Qwen3.6 Max Preview?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is MiMo-V2.5 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.5 and Qwen3.6 Max Preview share?
15 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3.6 Max Preview has 29.