# MiMo-V2.5 vs Qwen3.5 122B-A10B

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 42.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen3-5-122b-a10b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Qwen3.5 122B-A10B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5 leads 43.9 to 39.1.
- The biggest single-benchmark swing is SciCode: 43.1% for MiMo-V2.5 and 35.6% for Qwen3.5 122B-A10B.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 42.1 |
| Rank | 93 | 119 |
| Context | 1.05M | 262K |
| Input $/M | $0.14 | $0.40 |
| Output $/M | $0.28 | $3.20 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.9 (#81)
- Qwen3.5 122B-A10B: 39.1 (#162)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena WebDev | 1438 | 1360 |
| SciCode | 43.1% | 35.6% |
| LMArena Coding | 1469 | 1436 |
| ALE-Bench | 513.95 | — |

## Reasoning

- MiMo-V2.5: 28.6 (#101)
- Qwen3.5 122B-A10B: 27.2 (#123)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 3.7% | 0.9% |
| LMArena Hard Prompts | 1450 | 1421 |
| NYT Connections (extended) | — | 51.7% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |

## Math

- MiMo-V2.5: 36.8 (#163)
- Qwen3.5 122B-A10B: 39.1 (#112)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1436 | 1432 |
| ProofBench | 16% | — |

## Knowledge

- MiMo-V2.5: 40.8 (#115)
- Qwen3.5 122B-A10B: 38.8 (#142)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1460 | 1432 |
| Vectara Hallucination Rate | — | 11.2% |

## Multimodal

- MiMo-V2.5: 39.8 (#54)
- Qwen3.5 122B-A10B: 39.6 (#57)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1247 | 1245 |

## Multilingual

- MiMo-V2.5: 51.9 (#99)
- Qwen3.5 122B-A10B: 51.6 (#107)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1404 | 1400 |
| LMArena Chinese | 1468 | 1462 |
| LMArena French | 1447 | 1442 |
| LMArena German | 1421 | 1426 |
| LMArena Japanese | 1306 | 1367 |
| LMArena Korean | 1363 | 1352 |
| LMArena Russian | 1395 | 1400 |
| LMArena Spanish | 1416 | 1424 |

## Instruction Following

- MiMo-V2.5: 75.5 (#60)
- Qwen3.5 122B-A10B: 73.8 (#115)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1399 |

## Long Context

- MiMo-V2.5: 44.2 (#73)
- Qwen3.5 122B-A10B: 43.0 (#109)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1445 | 1410 |

## Writing & Preference

- MiMo-V2.5: 61.6 (#86)
- Qwen3.5 122B-A10B: 60.0 (#105)

| Benchmark | MiMo-V2.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1428 | 1417 |
| LMArena Creative Writing | 1393 | 1368 |
| LMArena Multi-Turn | 1445 | 1416 |

## FAQ

### Is MiMo-V2.5 better than Qwen3.5 122B-A10B?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 42.1 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Qwen3.5 122B-A10B?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.

### Is MiMo-V2.5 or Qwen3.5 122B-A10B better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 39.1 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 Qwen3.5 122B-A10B share?

21 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3.5 122B-A10B has 27.