# Mistral vs Mistral Large 3

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral scores higher in 1 category and Mistral Large 3 in 7 categories; 7 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 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral | Mistral Large 3 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.4 | 38.6 |
| Rank | 297 | 172 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Proprietary | Open |

## Coding

- Mistral: 33.2 (#249)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1162 | 1447 |
| LMArena WebDev | — | 1230 |

## Reasoning

- Mistral: 21.3 (#199)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |

## Math

- Mistral: 20.5 (#275)
- Mistral Large 3: 36.0 (#131)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1180 | 1415 |
| Omni-MATH | 7.2% | — |

## Knowledge

- Mistral: 16.3 (#283)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1125 | 1421 |
| MMLU-Pro | 27.7% | — |
| Vectara Hallucination Rate | — | 14.5% |
| GPQA (HELM) | 30.3% | — |

## Multimodal

- Mistral: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Mistral: 33.0 (#249)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1129 | 1412 |
| LMArena Chinese | 1109 | 1448 |
| LMArena French | 1179 | 1456 |
| LMArena German | 1155 | 1438 |
| LMArena Japanese | 1012 | 1399 |
| LMArena Korean | 1032 | 1384 |
| LMArena Russian | 1168 | 1412 |
| LMArena Spanish | 1143 | 1437 |

## Instruction Following

- Mistral: 52.9 (#283)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1152 | 1402 |
| IFEval | 56.8% | — |

## Long Context

- Mistral: 35.0 (#240)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1154 | 1413 |

## Writing & Preference

- Mistral: 37.2 (#255)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Mistral | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1165 | 1427 |
| LMArena Creative Writing | 1158 | 1385 |
| LMArena Multi-Turn | 1147 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
| WildBench | 66% | — |

## FAQ

### Is Mistral better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.

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

They score almost the same on coding (33.2 vs 34.1); test both on your own repository before choosing.

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

17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral Large 3 has 24.