# Mistral Large 4 vs Mistral Small

> Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.4 on the Noometry Index. Mistral Small costs 3.9× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-large-4-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Mistral Large 4 scores higher in 8 categories and Mistral Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 4 leads 40.4 to 16.4.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Large 4 | Mistral Small |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 43.1 | 33.4 |
| Rank | 99 | 243 |
| Context | 1.05M | 262K |
| Input $/M | $0.68 | $0.15 |
| Output $/M | $2.09 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Mistral Large 4: 48.6 (#57)
- Mistral Small: 34.0 (#247)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Coding | 1475 | 1362 |
| LMArena WebDev | 1541 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Mistral Large 4: —
- Mistral Small: 28.1 (#93)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Mistral Large 4: 22.5 (#192)
- Mistral Small: 19.8 (#250)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 27.4% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- Mistral Large 4: 40.4 (#91)
- Mistral Small: 16.4 (#293)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Math | 1488 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Mistral Large 4: 36.6 (#166)
- Mistral Small: 31.0 (#222)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Expert | 1447 | 1291 |
| GPQA Diamond | — | 47.5% |
| SimpleQA Verified | 20% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Mistral Large 4: —
- Mistral Small: 33.5 (#96)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- Mistral Large 4: 52.6 (#82)
- Mistral Small: 45.5 (#169)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1415 | 1315 |
| LMArena Chinese | 1491 | 1340 |
| LMArena Russian | 1414 | 1324 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Mistral Large 4: 75.0 (#76)
- Mistral Small: 66.4 (#209)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1424 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Mistral Large 4: 43.6 (#89)
- Mistral Small: 40.4 (#156)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1429 | 1327 |

## Writing & Preference

- Mistral Large 4: 60.4 (#97)
- Mistral Small: 52.5 (#171)

| Benchmark | Mistral Large 4 | Mistral Small |
|---|---|---|
| LMArena Text | 1427 | 1338 |
| LMArena Creative Writing | 1361 | 1305 |
| LMArena Multi-Turn | 1424 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Mistral Large 4 better than Mistral Small?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.4 on the Noometry Index. Mistral Small costs 3.9× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.

### Which is cheaper, Mistral Large 4 or Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.

### Is Mistral Large 4 or Mistral Small better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 262K.

### How many benchmarks do Mistral Large 4 and Mistral Small share?

12 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Mistral Small has 39.