# MiMo-V2-Flash vs Qwen2.5-VL 72B Instruct

> MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-flash-vs-qwen2-5-vl-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where MiMo-V2-Flash leads 24.1 to 20.0.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- MiMo-V2-Flash accepts more context: 262K tokens versus 131K.

## Snapshot

| | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 40.8 | 29.4 |
| Rank | 137 | 298 |
| Context | 262K | 131K |
| Input $/M | $0.14 | $2.80 |
| Output $/M | $0.28 | $8.40 |
| Weights | Open | Open |

## Coding

- MiMo-V2-Flash: 35.8 (#205)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| LMArena Coding | 1443 | — |
| ALE-Bench | 737.95 | — |

## Agentic & Tool Use

- MiMo-V2-Flash: —
- Qwen2.5-VL 72B Instruct: 18.4 (#136)

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |

## Reasoning

- MiMo-V2-Flash: 24.1 (#155)
- Qwen2.5-VL 72B Instruct: 20.0 (#228)

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1420 | — |

## Math

- MiMo-V2-Flash: 35.6 (#141)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Math | 1396 | — |

## Knowledge

- MiMo-V2-Flash: 39.1 (#126)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1425 | — |

## Multimodal

- MiMo-V2-Flash: —
- Qwen2.5-VL 72B Instruct: 32.9 (#92)

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |

## Multilingual

- MiMo-V2-Flash: 51.1 (#109)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1391 | — |
| LMArena Chinese | 1463 | — |
| LMArena French | 1429 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1324 | — |
| LMArena Korean | 1358 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1420 | — |

## Instruction Following

- MiMo-V2-Flash: 73.7 (#115)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1392 | — |

## Long Context

- MiMo-V2-Flash: 43.0 (#106)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1409 | — |

## Writing & Preference

- MiMo-V2-Flash: 59.9 (#101)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2-Flash | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1411 | — |
| LMArena Creative Writing | 1375 | — |
| LMArena Multi-Turn | 1404 | — |

## FAQ

### Is MiMo-V2-Flash better than Qwen2.5-VL 72B Instruct?

MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index.

### Which is cheaper, MiMo-V2-Flash or Qwen2.5-VL 72B Instruct?

MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

### Which has the bigger context window?

MiMo-V2-Flash does, with 262K tokens against 131K.

### How many benchmarks do MiMo-V2-Flash and Qwen2.5-VL 72B Instruct share?

0 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.