# Mistral Small 3 vs Mixtral 8x22B

> Mistral Small 3 is the stronger model overall, scoring 30.9 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Mistral Small 3 scores higher in 5 categories and Mixtral 8x22B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3 leads 36.0 to 23.8.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 34.1% for Mixtral 8x22B.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Mixtral 8x22B accepts more context: 64K tokens versus 33K.

## Snapshot

| | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.9 | 26.7 |
| Rank | 268 | 330 |
| Context | 33K | 64K |
| Input $/M | $0.05 | $2 |
| Output $/M | $0.08 | $6 |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.0 (#203)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 40.6% |
| LMArena Coding | 1246 | 1166 |
| BigCodeBench Complete | 50.4% | 50.2% |
| WeirdML | — | 3.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Mistral Small 3: —
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1150 |
| Epoch Capabilities Index | 127.06 | 122 |
| Chess Puzzles | 0% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |

## Math

- Mistral Small 3: 15.3 (#290)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1240 | 1184 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 47.3% | 34.1% |
| LMArena Expert | 1202 | 1113 |
| MMLU-Pro | — | 46% |
| Confabulations | 25.2% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1198 | 1128 |
| LMArena Chinese | 1204 | 1116 |
| LMArena French | 1202 | 1165 |
| LMArena German | 1211 | 1141 |
| LMArena Japanese | 1111 | 1037 |
| LMArena Korean | 1188 | 1056 |
| LMArena Russian | 1216 | 1158 |
| LMArena Spanish | — | 1150 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1246 | 1144 |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | Mistral Small 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1234 | 1162 |
| LMArena Creative Writing | 1195 | 1141 |
| LMArena Multi-Turn | 1217 | 1130 |
| EQ-Bench Creative Writing | 707 | — |
| WildBench | — | 71.1% |

## FAQ

### Is Mistral Small 3 better than Mixtral 8x22B?

Mistral Small 3 is the stronger model overall, scoring 30.9 to 26.7 on the Noometry Index.

### Which is cheaper, Mistral Small 3 or Mixtral 8x22B?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Mistral Small 3 or Mixtral 8x22B better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

Mixtral 8x22B does, with 64K tokens against 33K.

### How many benchmarks do Mistral Small 3 and Mixtral 8x22B share?

20 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Mixtral 8x22B has 34.