# Mistral Large vs Mistral Small 3.1

> Mistral Large and Mistral Small 3.1 score almost the same on the Noometry Index (31.9 vs 31.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-large-vs-mistral-small-3-1
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Mistral Large scores higher in 4 categories and Mistral Small 3.1 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 22.6.
- The biggest single-benchmark swing is IFEval: 87.7% for Mistral Large and 75% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.

## Snapshot

| | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 31.9 | 31.7 |
| Rank | 263 | 269 |
| Context | 131K | 128K |
| Input $/M | $2 | $0.35 |
| Output $/M | $6 | $0.56 |
| Weights | Open | Open |

## Coding

- Mistral Large: 34.3 (#240)
- Mistral Small 3.1: 38.3 (#179)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1277 | 1309 |
| 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 Large: 28.6 (#89)
- Mistral Small 3.1: —

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |

## Reasoning

- Mistral Large: 15.8 (#310)
- Mistral Small 3.1: 19.7 (#254)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1278 |
| Epoch Capabilities Index | 128.52 | 127.48 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |

## Math

- Mistral Large: 18.2 (#291)
- Mistral Small 3.1: 14.7 (#301)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 3.9% |
| Omni-MATH | 28.1% | 24.8% |
| LMArena Math | 1262 | 1262 |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Large: 30.1 (#230)
- Mistral Small 3.1: 22.6 (#271)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 51.3% | 41.9% |
| MMLU-Pro | 59.9% | 61% |
| GPQA (HELM) | 43.5% | 39.2% |
| LMArena Expert | 1232 | 1257 |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| MMLU | 80% | — |

## Multimodal

- Mistral Large: —
- Mistral Small 3.1: 33.2 (#99)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |

## Multilingual

- Mistral Large: 40.0 (#219)
- Mistral Small 3.1: 41.2 (#209)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1237 | 1255 |
| LMArena Chinese | 1240 | 1253 |
| LMArena French | 1325 | 1273 |
| LMArena German | 1254 | 1266 |
| LMArena Japanese | 1188 | 1208 |
| LMArena Korean | 1202 | 1206 |
| LMArena Russian | 1257 | 1263 |
| LMArena Spanish | 1268 | 1283 |

## Instruction Following

- Mistral Large: 67.9 (#191)
- Mistral Small 3.1: 63.6 (#230)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| IFEval | 87.7% | 75% |
| LMArena Instruction Following | 1249 | 1264 |
| LiveBench Instruction Following | 67.9% | — |

## Long Context

- Mistral Large: 38.3 (#199)
- Mistral Small 3.1: 39.5 (#178)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1261 | 1299 |

## Writing & Preference

- Mistral Large: 40.7 (#242)
- Mistral Small 3.1: 37.0 (#259)

| Benchmark | Mistral Large | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1266 | 1277 |
| LMArena Creative Writing | 1243 | 1253 |
| EQ-Bench Creative Writing | 985 | 761 |
| WildBench | 80.1% | 78.8% |
| LMArena Multi-Turn | 1260 | 1270 |
| Short-Story Creative Writing | 69% | — |
| LiveBench Language | 39.4% | — |

## FAQ

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

Mistral Large and Mistral Small 3.1 score almost the same on the Noometry Index (31.9 vs 31.7), so choose on price, context window or the category you care about most.

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

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Mistral Large lists at $2 and $6.

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

Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large does, with 131K tokens against 128K.

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

26 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Mistral Small 3.1 has 28.