# Codellama 70b Instruct vs Qwen2.5 72B Instruct

> Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Qwen2.5 72B Instruct in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2.5 72B Instruct leads 41.0 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 55.9% for Qwen2.5 72B Instruct.

## Snapshot

| | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 31.9 |
| Rank | 237 | 267 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 45.8% |
| BigCodeBench Complete | 49.6% | 55.9% |
| WeirdML | — | 16% |
| LMArena Coding | — | 1292 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Codellama 70b Instruct: —
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Codellama 70b Instruct: —
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 992 | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1024 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Codellama 70b Instruct: —
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Codellama 70b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1057 | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |

## FAQ

### Is Codellama 70b Instruct better than Qwen2.5 72B Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.9 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen2.5 72B Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.2 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Qwen2.5 72B Instruct share?

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen2.5 72B Instruct has 43.