# Codellama 34b Instruct vs Mixtral 8x22B

> Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Mixtral 8x22B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mixtral 8x22B leads 37.1 to 28.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 50.2% for Mixtral 8x22B.

## Snapshot

| | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.2 | 26.7 |
| Rank | 285 | 330 |
| Context | — | 64K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| BigCodeBench Instruct | 29% | 40.6% |
| LMArena Coding | 1046 | 1166 |
| BigCodeBench Complete | 37.1% | 50.2% |
| HumanEval+ | 43.9% | 72% |
| MBPP+ | 56.3% | 64.3% |
| WeirdML | — | 3.2% |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1150 |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122 |
| ForecastBench | — | 56.3 |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1056 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Codellama 34b Instruct: —
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| MMLU | — | 77.8% |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1011 | 1128 |
| LMArena Chinese | 976 | 1116 |
| LMArena French | — | 1165 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1056 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1150 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1014 | 1144 |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | Codellama 34b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1066 | 1162 |
| LMArena Creative Writing | 1032 | 1141 |
| LMArena Multi-Turn | 1015 | 1130 |
| WildBench | — | 71.1% |

## FAQ

### Is Codellama 34b Instruct better than Mixtral 8x22B?

Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 26.7 on the Noometry Index.

### Is Codellama 34b Instruct or Mixtral 8x22B better for coding?

Codellama 34b Instruct scores higher on coding benchmarks: 28.0 versus 23.8 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and Mixtral 8x22B share?

14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Mixtral 8x22B has 34.