# Codellama 34b Instruct vs Llama 3.2 90B

> Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Codellama 34b Instruct leads 28.5 to 10.4.

## Snapshot

| | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.2 | 27.1 |
| Rank | 285 | 326 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- Llama 3.2 90B: —

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| BigCodeBench Instruct | 29% | — |
| LMArena Coding | 1046 | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1032 | — |
| Epoch Capabilities Index | — | 125.5 |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1056 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Codellama 34b Instruct: —
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| MMLU | — | 80.3% |

## Multimodal

- Codellama 34b Instruct: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- Llama 3.2 90B: —

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- Llama 3.2 90B: —

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1028 | — |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- Llama 3.2 90B: —

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1014 | — |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- Llama 3.2 90B: —

| Benchmark | Codellama 34b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |

## FAQ

### Is Codellama 34b Instruct better than Llama 3.2 90B?

Codellama 34b Instruct is the stronger model overall, scoring 30.2 to 27.1 on the Noometry Index.

### How many benchmarks do Codellama 34b Instruct and Llama 3.2 90B share?

0 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Llama 3.2 90B has 9.