# MiMo-V2-Flash vs Qwen2-72B

> MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-flash-vs-qwen2-72b
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiMo-V2-Flash scores higher in 8 categories and Qwen2-72B 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 40.8.

## Snapshot

| | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 41.3 | 30.0 |
| Rank | 138 | 300 |
| Context | 262K | — |
| Input $/M | $0.14 | — |
| Output $/M | $0.28 | — |
| Weights | Open | Open |

## Coding

- MiMo-V2-Flash: 36.1 (#211)
- Qwen2-72B: 29.1 (#310)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1443 | 1196 |
| LMArena WebDev | 1330 | — |
| SciCode | 25.9% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 737.95 | — |

## Agentic & Tool Use

- MiMo-V2-Flash: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- MiMo-V2-Flash: 24.9 (#157)
- Qwen2-72B: 23.2 (#181)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1191 |
| CritPt | 0% | — |
| Epoch Capabilities Index | — | 125.28 |

## Math

- MiMo-V2-Flash: 38.3 (#139)
- Qwen2-72B: 30.2 (#236)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Math | 1396 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- MiMo-V2-Flash: 39.7 (#131)
- Qwen2-72B: 21.2 (#275)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1425 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- MiMo-V2-Flash: 51.0 (#113)
- Qwen2-72B: 35.9 (#244)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1392 | 1176 |
| LMArena Chinese | 1462 | 1240 |
| LMArena French | 1429 | 1170 |
| LMArena German | 1395 | 1151 |
| LMArena Japanese | 1325 | 1111 |
| LMArena Korean | 1358 | 1083 |
| LMArena Russian | 1387 | 1169 |
| LMArena Spanish | 1420 | 1169 |

## Instruction Following

- MiMo-V2-Flash: 73.5 (#120)
- Qwen2-72B: 61.7 (#241)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1392 | 1181 |

## Long Context

- MiMo-V2-Flash: 43.0 (#110)
- Qwen2-72B: 36.1 (#235)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1409 | 1192 |

## Writing & Preference

- MiMo-V2-Flash: 59.7 (#106)
- Qwen2-72B: 40.8 (#241)

| Benchmark | MiMo-V2-Flash | Qwen2-72B |
|---|---|---|
| LMArena Text | 1411 | 1203 |
| LMArena Creative Writing | 1375 | 1181 |
| LMArena Multi-Turn | 1404 | 1196 |

## FAQ

### Is MiMo-V2-Flash better than Qwen2-72B?

MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 30.0 on the Noometry Index.

### Is MiMo-V2-Flash or Qwen2-72B better for coding?

MiMo-V2-Flash scores higher on coding benchmarks: 36.1 versus 29.1 in the Noometry coding category.

### How many benchmarks do MiMo-V2-Flash and Qwen2-72B share?

17 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen2-72B has 26.