# Codestral vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and MiMo-V2.5 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5 leads 43.6 to 26.9.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 256K.

## Snapshot

| | Codestral | MiMo-V2.5 |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 30.1 | 43.0 |
| Rank | 287 | 89 |
| Context | 256K | 1.05M |
| Input $/M | $0.30 | $0.14 |
| Output $/M | $0.90 | $0.28 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| ALE-Bench | 137.78 | 513.95 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1469 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.1 (#244)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 3.7% |
| LMArena Hard Prompts | — | 1450 |

## Math

- Codestral: —
- MiMo-V2.5: 35.4 (#145)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1436 |

## Knowledge

- Codestral: —
- MiMo-V2.5: 40.2 (#109)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | — | 1459 |

## Multimodal

- Codestral: —
- MiMo-V2.5: 39.0 (#53)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Codestral: —
- MiMo-V2.5: 52.0 (#96)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | — | 1404 |
| LMArena Chinese | — | 1467 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1304 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1412 |

## Instruction Following

- Codestral: —
- MiMo-V2.5: 75.7 (#55)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1433 |

## Long Context

- Codestral: —
- MiMo-V2.5: 44.1 (#69)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | — | 1444 |

## Writing & Preference

- Codestral: —
- MiMo-V2.5: 61.8 (#82)

| Benchmark | Codestral | MiMo-V2.5 |
|---|---|---|
| LMArena Text | — | 1427 |
| LMArena Creative Writing | — | 1392 |
| LMArena Multi-Turn | — | 1445 |

## FAQ

### Is Codestral better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.1 on the Noometry Index.

### Which is cheaper, Codestral or MiMo-V2.5?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 256K.

### How many benchmarks do Codestral and MiMo-V2.5 share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and MiMo-V2.5 has 23.