# Mistral Small 3 vs Mixtral 8x7B

> Mistral Small 3 is the stronger model overall, scoring 30.9 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 6 categories and Mixtral 8x7B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.0 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 30.6% for Mixtral 8x7B.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Mistral Small 3 accepts more context: 33K tokens versus 32K.

## Snapshot

| | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.9 | 26.8 |
| Rank | 268 | 328 |
| Context | 33K | 32K |
| Input $/M | $0.05 | $0.70 |
| Output $/M | $0.08 | $0.70 |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.0 (#203)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1246 | 1127 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1115 |
| Epoch Capabilities Index | 127.06 | 118.38 |
| Chess Puzzles | 0% | — |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |

## Math

- Mistral Small 3: 15.3 (#290)
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1240 | 1147 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 47.3% | 30.6% |
| LMArena Expert | 1202 | 1088 |
| MMLU-Pro | — | 33.5% |
| Confabulations | 25.2% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1198 | 1077 |
| LMArena Chinese | 1204 | 1055 |
| LMArena French | 1202 | 1165 |
| LMArena German | 1211 | 1114 |
| LMArena Japanese | 1111 | 931 |
| LMArena Korean | 1188 | 968 |
| LMArena Russian | 1216 | 1090 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1110 |
| IFEval | — | 57.5% |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1246 | 1103 |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | Mistral Small 3 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1234 | 1132 |
| LMArena Creative Writing | 1195 | 1109 |
| LMArena Multi-Turn | 1217 | 1115 |
| EQ-Bench Creative Writing | 707 | — |
| WildBench | — | 67.3% |

## FAQ

### Is Mistral Small 3 better than Mixtral 8x7B?

Mistral Small 3 is the stronger model overall, scoring 30.9 to 26.8 on the Noometry Index.

### Which is cheaper, Mistral Small 3 or Mixtral 8x7B?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

### Is Mistral Small 3 or Mixtral 8x7B better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 32.2 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small 3 does, with 33K tokens against 32K.

### How many benchmarks do Mistral Small 3 and Mixtral 8x7B share?

18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Mixtral 8x7B has 38.