# Codellama 70b Instruct vs Mixtral 8x7B

> Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and Mixtral 8x7B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mixtral 8x7B leads 29.8 to 24.9.

## Snapshot

| | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.3 | 26.8 |
| Rank | 236 | 328 |
| Context | — | 32K |
| Input $/M | — | $0.70 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| HumanEval+ | 65.9% | 39.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1127 |
| BigCodeBench Complete | 49.6% | — |
| MBPP+ | — | 49.7% |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1115 |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| Epoch Capabilities Index | — | 118.38 |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |

## Math

- Codellama 70b Instruct: —
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | — | 10.5% |
| LMArena Math | — | 1147 |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |

## Knowledge

- Codellama 70b Instruct: —
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| LMArena Expert | — | 1088 |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 992 | 1077 |
| LMArena Chinese | — | 1055 |
| LMArena French | — | 1165 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 931 |
| LMArena Korean | — | 968 |
| LMArena Russian | — | 1090 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1110 |
| IFEval | — | 57.5% |

## Long Context

- Codellama 70b Instruct: —
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | — | 1103 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | Codellama 70b Instruct | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1057 | 1132 |
| LMArena Creative Writing | — | 1109 |
| WildBench | — | 67.3% |
| LMArena Multi-Turn | — | 1115 |

## FAQ

### Is Codellama 70b Instruct better than Mixtral 8x7B?

Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 26.8 on the Noometry Index.

### Is Codellama 70b Instruct or Mixtral 8x7B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 32.2 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Mixtral 8x7B share?

5 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mixtral 8x7B has 38.