# MiMo-V2.5 vs Qwen2.5-Coder-32B

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen2-5-coder-32b
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5 leads 43.9 to 22.6.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 33K.

## Snapshot

| | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 33.4 |
| Rank | 93 | 245 |
| Context | 1.05M | 33K |
| Input $/M | $0.14 | $0.66 |
| Output $/M | $0.28 | $1 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.9 (#81)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1469 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 513.95 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- MiMo-V2.5: 28.6 (#101)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1251 |
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- MiMo-V2.5: 36.8 (#163)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1436 | 1251 |
| ProofBench | 16% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- MiMo-V2.5: 40.8 (#115)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1460 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multimodal

- MiMo-V2.5: 39.8 (#54)
- Qwen2.5-Coder-32B: —

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1247 | — |

## Multilingual

- MiMo-V2.5: 51.9 (#99)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1404 | 1205 |
| LMArena Chinese | 1468 | 1222 |
| LMArena Russian | 1395 | 1228 |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
| LMArena Spanish | 1416 | — |

## Instruction Following

- MiMo-V2.5: 75.5 (#60)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- MiMo-V2.5: 44.2 (#73)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1445 | 1251 |

## Writing & Preference

- MiMo-V2.5: 61.6 (#86)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | MiMo-V2.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1428 | 1230 |
| LMArena Creative Writing | 1393 | 1174 |
| LMArena Multi-Turn | 1445 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is MiMo-V2.5 better than Qwen2.5-Coder-32B?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.4 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Qwen2.5-Coder-32B?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

### Is MiMo-V2.5 or Qwen2.5-Coder-32B better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 22.6 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 Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen2.5-Coder-32B has 31.