# Ministral 3B vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 26.2 on the Noometry Index. Ministral 3B costs 30× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/ministral-3b-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Ministral 3B scores higher in 0 categories and Mistral Medium in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium leads 25.0 to 10.4.
- The biggest single-benchmark swing is MATH Level 5: 14.4% for Ministral 3B and 81.6% for Mistral Medium.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.

## Snapshot

| | Ministral 3B | Mistral Medium |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 26.2 | 36.3 |
| Rank | 338 | 218 |
| Context | 131K | 262K |
| Input $/M | $0.10 | $1.50 |
| Output $/M | $0.10 | $7.50 |
| Weights | Open | Open |

## Coding

- Ministral 3B: —
- Mistral Medium: 34.2 (#243)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| LMArena Coding | — | 1434 |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Ministral 3B: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Ministral 3B: 18.4 (#282)
- Mistral Medium: 24.0 (#167)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| DTBench | 51.7% | 75.5% |
| LMCA | 5.5% | 26.1% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1426 |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 118.1 | — |

## Math

- Ministral 3B: 26.6 (#258)
- Mistral Medium: 28.1 (#245)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| MATH Level 5 | 14.4% | 81.6% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LMArena Math | — | 1408 |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Ministral 3B: 10.4 (#302)
- Mistral Medium: 25.0 (#265)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 25.3% | 59.5% |
| Vectara Hallucination Rate | 7.3% | 22.7% |
| Humanity's Last Exam | — | 4.5% |
| LMArena Expert | — | 1408 |

## Multimodal

- Ministral 3B: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Ministral 3B: —
- Mistral Medium: 52.1 (#91)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |

## Instruction Following

- Ministral 3B: —
- Mistral Medium: 73.7 (#116)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |

## Long Context

- Ministral 3B: —
- Mistral Medium: 42.9 (#114)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |

## Writing & Preference

- Ministral 3B: —
- Mistral Medium: 60.0 (#103)

| Benchmark | Ministral 3B | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |

## FAQ

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

Mistral Medium is the stronger model overall, scoring 36.3 to 26.2 on the Noometry Index. Ministral 3B costs 30× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

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

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Which has the bigger context window?

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

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

5 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Mistral Medium has 36.