# MiMo-V2.5-Pro vs Mixtral 8x22B

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-pro-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 37.1.
- The biggest single-benchmark swing is DTBench: 84.5% for MiMo-V2.5-Pro and 55.1% for Mixtral 8x22B.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 64K.

## Snapshot

| | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 44.8 | 26.7 |
| Rank | 70 | 330 |
| Context | 1.05M | 64K |
| Input $/M | $0.43 | $2 |
| Output $/M | $0.87 | $6 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5-Pro: 47.0 (#58)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1502 | 1166 |
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 899.8 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- MiMo-V2.5-Pro: —
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- MiMo-V2.5-Pro: 25.9 (#124)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1487 | 1150 |
| DTBench | 84.5% | 55.1% |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 122 |
| ForecastBench | — | 56.3 |

## Math

- MiMo-V2.5-Pro: 38.6 (#84)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1480 | 1184 |
| ProofBench | 22% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- MiMo-V2.5-Pro: 41.5 (#100)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1501 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- MiMo-V2.5-Pro: 55.3 (#33)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1449 | 1128 |
| LMArena Chinese | 1507 | 1116 |
| LMArena French | 1489 | 1165 |
| LMArena German | 1455 | 1141 |
| LMArena Japanese | 1418 | 1037 |
| LMArena Korean | 1436 | 1056 |
| LMArena Russian | 1450 | 1158 |
| LMArena Spanish | 1470 | 1150 |

## Instruction Following

- MiMo-V2.5-Pro: 77.6 (#21)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- MiMo-V2.5-Pro: 45.4 (#38)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1482 | 1144 |

## Writing & Preference

- MiMo-V2.5-Pro: 65.5 (#47)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | MiMo-V2.5-Pro | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1465 | 1162 |
| LMArena Creative Writing | 1440 | 1141 |
| LMArena Multi-Turn | 1477 | 1130 |
| EQ-Bench Creative Writing | 1493 | — |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 1208 | — |

## FAQ

### Is MiMo-V2.5-Pro better than Mixtral 8x22B?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 26.7 on the Noometry Index.

### Which is cheaper, MiMo-V2.5-Pro or Mixtral 8x22B?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is MiMo-V2.5-Pro or Mixtral 8x22B better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 64K.

### How many benchmarks do MiMo-V2.5-Pro and Mixtral 8x22B share?

18 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Mixtral 8x22B has 34.