# Devstral Small 2505 vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.6× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/devstral-small-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and MiMo-V2.6-Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 60.9% for MiMo-V2.6-Pro.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| Provider | Mistral AI | Xiaomi |
| Noometry Index | 34.3 | 50.3 |
| Rank | 233 | 49 |
| Context | 128K | 1.05M |
| Input $/M | $0.10 | $0.43 |
| Output $/M | $0.30 | $0.87 |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| SciCode | 28.8% | 60.9% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1629 |
| LMArena Coding | — | 1534 |
| ALE-Bench | — | 1,158 |

## Agentic & Tool Use

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 0% | 26.6% |
| Kagi LLM Benchmark | 37.7% | — |
| LMArena Hard Prompts | — | 1512 |

## Math

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | — | 70% |
| LMArena Math | — | 1494 |

## Knowledge

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | — | 1543 |

## Multimodal

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1529 |
| LMArena Russian | — | 1480 |

## Instruction Following

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1493 |

## Long Context

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | — | 1501 |

## Writing & Preference

- Devstral Small 2505: —
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | Devstral Small 2505 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | — | 1492 |
| LMArena Creative Writing | — | 1468 |
| LMArena Multi-Turn | — | 1464 |

## FAQ

### Is Devstral Small 2505 better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.6× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

### Which is cheaper, Devstral Small 2505 or MiMo-V2.6-Pro?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is Devstral Small 2505 or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 128K.

### How many benchmarks do Devstral Small 2505 and MiMo-V2.6-Pro share?

2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and MiMo-V2.6-Pro has 19.