# Gemma 3 27B vs Mixtral 8x7B

> Gemma 3 27B is the stronger model overall, scoring 30.5 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-27b-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and Mixtral 8x7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 27B leads 70.8 to 51.2.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 10% for Mixtral 8x7B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Gemma 3 27B accepts more context: 131K tokens versus 32K.

## Snapshot

| | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 30.5 | 26.8 |
| Rank | 277 | 328 |
| Context | 131K | 32K |
| Input $/M | $0.08 | $0.70 |
| Output $/M | $0.16 | $0.70 |
| Weights | Open | Open |

## Coding

- Gemma 3 27B: 22.1 (#329)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1322 | 1127 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |

## Agentic & Tool Use

- Gemma 3 27B: 24.9 (#105)
- Mixtral 8x7B: —

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |

## Reasoning

- Gemma 3 27B: 16.3 (#297)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1115 |
| DTBench | 52.5% | 49.6% |
| Epoch Capabilities Index | 130.04 | 118.38 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| LiveBench | 50% | — |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |

## Math

- Gemma 3 27B: 24.4 (#261)
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1312 | 1147 |
| MATH Level 5 | 74% | 10% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| Omni-MATH | — | 10.5% |
| LiveBench Math | 55.4% | — |
| GSM8K | — | 74.4% |

## Knowledge

- Gemma 3 27B: 25.4 (#256)
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 47.7% | 30.6% |
| LMArena Expert | 1303 | 1088 |
| MMLU-Pro | — | 33.5% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |

## Multimodal

- Gemma 3 27B: 32.0 (#94)
- Mixtral 8x7B: —

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |

## Multilingual

- Gemma 3 27B: 47.0 (#150)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1334 | 1077 |
| LMArena Chinese | 1347 | 1055 |
| LMArena French | 1368 | 1165 |
| LMArena German | 1362 | 1114 |
| LMArena Japanese | 1287 | 931 |
| LMArena Korean | 1308 | 968 |
| LMArena Russian | 1349 | 1090 |
| LMArena Spanish | 1348 | 1110 |

## Instruction Following

- Gemma 3 27B: 70.8 (#155)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1110 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 57.5% |

## Long Context

- Gemma 3 27B: 27.6 (#288)
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1333 | 1103 |
| Fiction.LiveBench | 33.3% | — |

## Writing & Preference

- Gemma 3 27B: 52.7 (#161)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1358 | 1132 |
| LMArena Creative Writing | 1346 | 1109 |
| LMArena Multi-Turn | 1344 | 1115 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| WildBench | — | 67.3% |
| LiveBench Language | 34.6% | — |

## FAQ

### Is Gemma 3 27B better than Mixtral 8x7B?

Gemma 3 27B is the stronger model overall, scoring 30.5 to 26.8 on the Noometry Index.

### Which is cheaper, Gemma 3 27B or Mixtral 8x7B?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

### Is Gemma 3 27B or Mixtral 8x7B better for coding?

Mixtral 8x7B scores higher on coding benchmarks: 32.2 versus 22.1 in the Noometry coding category.

### Which has the bigger context window?

Gemma 3 27B does, with 131K tokens against 32K.

### How many benchmarks do Gemma 3 27B and Mixtral 8x7B share?

21 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Mixtral 8x7B has 38.