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

> MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 33.4 on the Noometry Index.

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

## Summary

- They share 12 benchmarks with published results for both. MiMo-V2-Flash 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 writing & preference, where MiMo-V2-Flash leads 59.7 to 41.6.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- MiMo-V2-Flash accepts more context: 262K tokens versus 33K.

## Snapshot

| | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 41.3 | 33.4 |
| Rank | 138 | 245 |
| Context | 262K | 33K |
| Input $/M | $0.14 | $0.66 |
| Output $/M | $0.28 | $1 |
| Weights | Open | Open |

## Coding

- MiMo-V2-Flash: 36.1 (#211)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1443 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 737.95 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- MiMo-V2-Flash: 24.9 (#157)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1251 |
| CritPt | 0% | — |
| 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-Flash: 38.3 (#139)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1396 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- MiMo-V2-Flash: 39.7 (#131)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1425 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- MiMo-V2-Flash: 51.0 (#113)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1392 | 1205 |
| LMArena Chinese | 1462 | 1222 |
| LMArena Russian | 1387 | 1228 |
| LMArena French | 1429 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1325 | — |
| LMArena Korean | 1358 | — |
| LMArena Spanish | 1420 | — |

## Instruction Following

- MiMo-V2-Flash: 73.5 (#120)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1392 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- MiMo-V2-Flash: 43.0 (#110)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1409 | 1251 |

## Writing & Preference

- MiMo-V2-Flash: 59.7 (#106)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | MiMo-V2-Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1411 | 1230 |
| LMArena Creative Writing | 1375 | 1174 |
| LMArena Multi-Turn | 1404 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

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

MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 33.4 on the Noometry Index.

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

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

MiMo-V2-Flash scores higher on coding benchmarks: 36.1 versus 22.6 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Flash does, with 262K tokens against 33K.

### How many benchmarks do MiMo-V2-Flash and Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen2.5-Coder-32B has 31.