# Mistral vs Mistral Large

> Mistral Large is the stronger model overall, scoring 31.6 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Mistral scores higher in 2 categories and Mistral Large in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Large leads 68.1 to 52.9.
- The biggest single-benchmark swing is MMLU-Pro: 27.7% for Mistral and 59.9% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral | Mistral Large |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.4 | 31.6 |
| Rank | 297 | 258 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Open |

## Coding

- Mistral: 33.2 (#249)
- Mistral Large: 33.8 (#240)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| LMArena Coding | 1162 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Mistral: —
- Mistral Large: 28.4 (#83)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- Mistral: 21.3 (#199)
- Mistral Large: 15.4 (#305)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1257 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Mistral: 20.5 (#275)
- Mistral Large: 17.1 (#285)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| Omni-MATH | 7.2% | 28.1% |
| LMArena Math | 1180 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Mistral: 16.3 (#283)
- Mistral Large: 30.0 (#224)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| MMLU-Pro | 27.7% | 59.9% |
| GPQA (HELM) | 30.3% | 43.5% |
| LMArena Expert | 1125 | 1232 |
| GPQA Diamond | — | 51.3% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| MMLU | — | 80% |

## Multilingual

- Mistral: 33.0 (#249)
- Mistral Large: 40.1 (#214)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| LMArena Non-English | 1129 | 1237 |
| LMArena Chinese | 1109 | 1240 |
| LMArena French | 1179 | 1324 |
| LMArena German | 1155 | 1254 |
| LMArena Japanese | 1012 | 1187 |
| LMArena Korean | 1032 | 1202 |
| LMArena Russian | 1168 | 1257 |
| LMArena Spanish | 1143 | 1268 |

## Instruction Following

- Mistral: 52.9 (#283)
- Mistral Large: 68.1 (#186)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| IFEval | 56.8% | 87.7% |
| LMArena Instruction Following | 1152 | 1249 |
| LiveBench Instruction Following | — | 67.9% |

## Long Context

- Mistral: 35.0 (#240)
- Mistral Large: 38.3 (#194)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1154 | 1262 |

## Writing & Preference

- Mistral: 37.2 (#255)
- Mistral Large: 40.9 (#237)

| Benchmark | Mistral | Mistral Large |
|---|---|---|
| LMArena Text | 1165 | 1266 |
| LMArena Creative Writing | 1158 | 1243 |
| WildBench | 66% | 80.1% |
| LMArena Multi-Turn | 1147 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Mistral better than Mistral Large?

Mistral Large is the stronger model overall, scoring 31.6 to 29.4 on the Noometry Index.

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

They score almost the same on coding (33.2 vs 33.8); test both on your own repository before choosing.

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

22 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral Large has 51.