# Ministral 8B vs Mistral Small 3

> Mistral Small 3 is the stronger model overall, scoring 30.9 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ministral-8b-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Ministral 8B scores higher in 2 categories and Mistral Small 3 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.0 to 12.5.
- The biggest single-benchmark swing is GPQA Diamond: 27.1% for Ministral 8B and 47.3% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.10 for Ministral 8B.
- Ministral 8B accepts more context: 128K tokens versus 33K.

## Snapshot

| | Ministral 8B | Mistral Small 3 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 27.8 | 30.9 |
| Rank | 321 | 268 |
| Context | 128K | 33K |
| Input $/M | $0.10 | $0.05 |
| Output $/M | $0.10 | $0.08 |
| Weights | Open | Open |

## Coding

- Ministral 8B: 34.4 (#226)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1202 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Agentic & Tool Use

- Ministral 8B: 16.2 (#140)
- Mistral Small 3: —

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |

## Reasoning

- Ministral 8B: 17.7 (#279)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1233 |
| Chess Puzzles | — | 0% |
| DTBench | 45.7% | — |
| Epoch Capabilities Index | — | 127.06 |

## Math

- Ministral 8B: 23.7 (#262)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1188 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Ministral 8B: 12.5 (#292)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 27.1% | 47.3% |
| LMArena Expert | 1170 | 1202 |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 7.4% | — |

## Multilingual

- Ministral 8B: 35.3 (#242)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1165 | 1198 |
| LMArena Chinese | 1193 | 1204 |
| LMArena Russian | 1195 | 1216 |
| LMArena French | — | 1202 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |

## Instruction Following

- Ministral 8B: 60.7 (#245)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1161 | 1214 |

## Long Context

- Ministral 8B: 36.7 (#222)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1212 | 1246 |

## Writing & Preference

- Ministral 8B: 39.8 (#241)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Ministral 8B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1191 | 1234 |
| LMArena Creative Writing | 1175 | 1195 |
| LMArena Multi-Turn | 1166 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Ministral 8B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 30.9 to 27.8 on the Noometry Index.

### Which is cheaper, Ministral 8B or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Ministral 8B lists at $0.10 and $0.10.

### Is Ministral 8B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Ministral 8B does, with 128K tokens against 33K.

### How many benchmarks do Ministral 8B and Mistral Small 3 share?

13 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Mistral Small 3 has 24.
