# Devstral Small 2505 vs MiniMax-M2.1

> MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 33.9 on the Noometry Index. Devstral Small 2505 costs 3.5× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/devstral-small-vs-minimax-m2-1
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Devstral Small 2505 leads 19.1 to 15.8.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 128K.

## Snapshot

| | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 33.9 | 38.4 |
| Rank | 228 | 177 |
| Context | 128K | 205K |
| Input $/M | $0.10 | $0.30 |
| Output $/M | $0.30 | $1.20 |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.6 (#160)
- MiniMax-M2.1: 40.1 (#132)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1384 |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1421 |
| ALE-Bench | — | 623.83 |

## Agentic & Tool Use

- Devstral Small 2505: —
- MiniMax-M2.1: 27.7 (#91)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- MiniMax-M2.1: 15.8 (#301)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1410 |

## Math

- Devstral Small 2505: —
- MiniMax-M2.1: 35.6 (#142)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | — | 1396 |

## Knowledge

- Devstral Small 2505: —
- MiniMax-M2.1: 37.7 (#143)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1432 |

## Multilingual

- Devstral Small 2505: —
- MiniMax-M2.1: 50.2 (#123)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | — | 1378 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1405 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1297 |
| LMArena Russian | — | 1386 |
| LMArena Spanish | — | 1396 |

## Instruction Following

- Devstral Small 2505: —
- MiniMax-M2.1: 74.0 (#108)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | — | 1399 |

## Long Context

- Devstral Small 2505: —
- MiniMax-M2.1: 43.2 (#98)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | — | 1416 |

## Writing & Preference

- Devstral Small 2505: —
- MiniMax-M2.1: 58.5 (#114)

| Benchmark | Devstral Small 2505 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | — | 1392 |
| LMArena Creative Writing | — | 1362 |
| LMArena Multi-Turn | — | 1396 |

## FAQ

### Is Devstral Small 2505 better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 33.9 on the Noometry Index. Devstral Small 2505 costs 3.5× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

### Which is cheaper, Devstral Small 2505 or MiniMax-M2.1?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

### Is Devstral Small 2505 or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 128K.

### How many benchmarks do Devstral Small 2505 and MiniMax-M2.1 share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and MiniMax-M2.1 has 22.