# Codellama 34b Instruct vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Coder-32B leads 41.8 to 28.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 58% for Qwen2.5-Coder-32B.

## Snapshot

| | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.2 | 32.9 |
| Rank | 285 | 239 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 29% | 49% |
| LMArena Coding | 1046 | 1276 |
| BigCodeBench Complete | 37.1% | 58% |
| HumanEval+ | 43.9% | 87.2% |
| MBPP+ | 56.3% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1056 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Codellama 34b Instruct: —
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1011 | 1205 |
| LMArena Chinese | 976 | 1222 |
| LMArena Russian | — | 1228 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1014 | 1251 |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | Codellama 34b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1066 | 1230 |
| LMArena Creative Writing | 1032 | 1174 |
| LMArena Multi-Turn | 1015 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Codellama 34b Instruct better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 30.2 on the Noometry Index.

### Is Codellama 34b Instruct or Qwen2.5-Coder-32B better for coding?

Codellama 34b Instruct scores higher on coding benchmarks: 28.0 versus 22.4 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen2.5-Coder-32B has 31.