# Llama 13b vs Mixtral 8x7B

> Mixtral 8x7B is the stronger model overall, scoring 26.8 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-13b-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 13b scores higher in 1 category and Mixtral 8x7B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mixtral 8x7B leads 34.4 to 13.9.

## Snapshot

| | Llama 13b | Mixtral 8x7B |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.9 | 26.8 |
| Rank | 344 | 328 |
| Context | — | 32K |
| Input $/M | — | $0.70 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- Llama 13b: 20.9 (#332)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 683 | 1127 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |

## Reasoning

- Llama 13b: 13.4 (#327)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1115 |
| Epoch Capabilities Index | 100.09 | 118.38 |
| HellaSwag | 79.2% | 86.7% |
| PIQA | 80.1% | 83.6% |
| WinoGrande | 73% | 77.2% |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| BIG-Bench Hard | 37.9% | — |
| ForecastBench | — | 56.3 |
| LAMBADA | 75.2% | — |

## Math

- Llama 13b: 24.4 (#259)
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 838 | 1147 |
| GSM8K | 20.6% | 74.4% |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |

## Knowledge

- Llama 13b: —
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 87.3% |
| MMLU | 47.7% | 70.6% |
| OpenBookQA | 56.4% | 85.8% |
| TriviaQA | 77.9% | 82.2% |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| LMArena Expert | — | 1088 |
| BoolQ | 78.7% | — |

## Multimodal

- Llama 13b: —
- Mixtral 8x7B: —

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.8 (#292)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 819 | 1077 |
| LMArena Chinese | — | 1055 |
| LMArena French | — | 1165 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 931 |
| LMArena Korean | — | 968 |
| LMArena Russian | — | 1090 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Llama 13b: 36.9 (#300)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 781 | 1110 |
| IFEval | — | 57.5% |

## Long Context

- Llama 13b: —
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | — | 1103 |

## Writing & Preference

- Llama 13b: 13.9 (#307)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | Llama 13b | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 834 | 1132 |
| LMArena Creative Writing | 794 | 1109 |
| LMArena Multi-Turn | 753 | 1115 |
| WildBench | — | 67.3% |

## FAQ

### Is Llama 13b better than Mixtral 8x7B?

Mixtral 8x7B is the stronger model overall, scoring 26.8 to 23.9 on the Noometry Index.

### Is Llama 13b or Mixtral 8x7B better for coding?

Mixtral 8x7B scores higher on coding benchmarks: 32.2 versus 20.9 in the Noometry coding category.

### How many benchmarks do Llama 13b and Mixtral 8x7B share?

17 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Mixtral 8x7B has 38.