# Magistral Medium vs Ministral 3B

> Magistral Medium is the stronger model overall, scoring 35.2 to 26.2 on the Noometry Index. Ministral 3B costs 28× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-ministral-3b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 10.4.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.

## Snapshot

| | Magistral Medium | Ministral 3B |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 26.2 |
| Rank | 227 | 338 |
| Context | 262K | 131K |
| Input $/M | $2 | $0.10 |
| Output $/M | $5 | $0.10 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 39.1 (#161)
- Ministral 3B: —

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| SciCode | 39.2% | — |
| LMArena Coding | 1319 | — |

## Reasoning

- Magistral Medium: 8.6 (#348)
- Ministral 3B: 18.4 (#282)

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LMArena Hard Prompts | 1267 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 118.1 |

## Math

- Magistral Medium: 35.1 (#189)
- Ministral 3B: 26.6 (#258)

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| LMArena Math | 1250 | — |
| MATH Level 5 | — | 14.4% |

## Knowledge

- Magistral Medium: 33.5 (#202)
- Ministral 3B: 10.4 (#302)

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| GPQA Diamond | — | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1223 | — |

## Multilingual

- Magistral Medium: 39.6 (#224)
- Ministral 3B: —

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1232 | — |
| LMArena Chinese | 1227 | — |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |

## Instruction Following

- Magistral Medium: 66.0 (#211)
- Ministral 3B: —

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1254 | — |

## Long Context

- Magistral Medium: 39.3 (#183)
- Ministral 3B: —

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1295 | — |

## Writing & Preference

- Magistral Medium: 46.3 (#219)
- Ministral 3B: —

| Benchmark | Magistral Medium | Ministral 3B |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |

## FAQ

### Is Magistral Medium better than Ministral 3B?

Magistral Medium is the stronger model overall, scoring 35.2 to 26.2 on the Noometry Index. Ministral 3B costs 28× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

### Which is cheaper, Magistral Medium or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Magistral Medium lists at $2 and $5.

### Which has the bigger context window?

Magistral Medium does, with 262K tokens against 131K.

### How many benchmarks do Magistral Medium and Ministral 3B share?

0 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Ministral 3B has 6.