# Gemma 3 4B vs Mixtral 8x22B

> Gemma 3 4B and Mixtral 8x22B score almost the same on the Noometry Index (28.1 vs 27.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-mixtral-8x22b
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Mixtral 8x22B in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 3 4B leads 35.9 to 24.2.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 34.1% for Mixtral 8x22B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Gemma 3 4B accepts more context: 131K tokens versus 64K.

## Snapshot

| | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 28.1 | 27.1 |
| Rank | 326 | 333 |
| Context | 131K | 64K |
| Input $/M | $0.04 | $2 |
| Output $/M | $0.08 | $6 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.9 (#215)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1230 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Gemma 3 4B: 20.9 (#142)
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
| Cybench | — | 7.5% |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1150 |
| DTBench | 50.9% | 55.1% |
| Epoch Capabilities Index | 116.02 | 122.03 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMCA | 2.8% | — |
| ForecastBench | — | 56.3 |

## Math

- Gemma 3 4B: 16.8 (#292)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1239 | 1184 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 23.2% | 34.1% |
| LMArena Expert | 1223 | 1113 |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 6.4% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1273 | 1128 |
| LMArena German | 1281 | 1141 |
| LMArena Russian | 1294 | 1158 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1166 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Spanish | — | 1151 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1273 | 1144 |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | Gemma 3 4B | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1291 | 1162 |
| LMArena Creative Writing | 1271 | 1141 |
| LMArena Multi-Turn | 1255 | 1130 |
| EQ-Bench Creative Writing | 1068 | — |
| WildBench | — | 71.1% |

## FAQ

### Is Gemma 3 4B better than Mixtral 8x22B?

Gemma 3 4B and Mixtral 8x22B score almost the same on the Noometry Index (28.1 vs 27.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 3 4B or Mixtral 8x22B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Gemma 3 4B or Mixtral 8x22B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Gemma 3 4B does, with 131K tokens against 64K.

### How many benchmarks do Gemma 3 4B and Mixtral 8x22B share?

15 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mixtral 8x22B has 34.