# Mistral Large 3 vs Mistral Small 3.1

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-3-vs-mistral-small-3-1
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Mistral Large 3 scores higher in 7 categories and Mistral Small 3.1 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 37.2.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.

## Snapshot

| | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 38.6 | 31.4 |
| Rank | 172 | 263 |
| Context | 262K | 128K |
| Input $/M | $0.25 | $0.35 |
| Output $/M | $0.75 | $0.56 |
| Weights | Open | Open |

## Coding

- Mistral Large 3: 34.1 (#230)
- Mistral Small 3.1: 37.7 (#175)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1447 | 1309 |
| LMArena WebDev | 1230 | — |

## Reasoning

- Mistral Large 3: 14.6 (#314)
- Mistral Small 3.1: 18.9 (#249)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1278 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Chess Puzzles | — | 1% |
| Thematic Generalization | 23% | — |
| Epoch Capabilities Index | — | 127.48 |

## Math

- Mistral Large 3: 36.0 (#131)
- Mistral Small 3.1: 13.7 (#295)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Math | 1415 | 1261 |
| OTIS Mock AIME 2024-2025 | — | 3.9% |
| Omni-MATH | — | 24.8% |

## Knowledge

- Mistral Large 3: 35.5 (#173)
- Mistral Small 3.1: 22.6 (#266)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Expert | 1421 | 1258 |
| GPQA Diamond | — | 41.9% |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 14.5% | — |
| GPQA (HELM) | — | 39.2% |

## Multimodal

- Mistral Large 3: 37.6 (#65)
- Mistral Small 3.1: 32.6 (#93)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1222 | 1136 |

## Multilingual

- Mistral Large 3: 52.6 (#79)
- Mistral Small 3.1: 41.4 (#204)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1412 | 1255 |
| LMArena Chinese | 1448 | 1254 |
| LMArena French | 1456 | 1270 |
| LMArena German | 1438 | 1266 |
| LMArena Japanese | 1399 | 1210 |
| LMArena Korean | 1384 | 1206 |
| LMArena Russian | 1412 | 1263 |
| LMArena Spanish | 1437 | 1283 |

## Instruction Following

- Mistral Large 3: 74.1 (#104)
- Mistral Small 3.1: 63.8 (#225)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1402 | 1264 |
| IFEval | — | 75% |

## Long Context

- Mistral Large 3: 43.1 (#102)
- Mistral Small 3.1: 39.5 (#172)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1413 | 1300 |

## Writing & Preference

- Mistral Large 3: 60.2 (#100)
- Mistral Small 3.1: 37.2 (#254)

| Benchmark | Mistral Large 3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1427 | 1278 |
| LMArena Creative Writing | 1385 | 1253 |
| EQ-Bench Creative Writing | 1412 | 761 |
| LMArena Multi-Turn | 1429 | 1270 |
| WildBench | — | 78.8% |

## FAQ

### Is Mistral Large 3 better than Mistral Small 3.1?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.4 on the Noometry Index.

### Which is cheaper, Mistral Large 3 or Mistral Small 3.1?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.

### Is Mistral Large 3 or Mistral Small 3.1 better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 128K.

### How many benchmarks do Mistral Large 3 and Mistral Small 3.1 share?

19 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Mistral Small 3.1 has 28.