# Codellama 70b Instruct vs Qwen1.5-72B

> Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwen1-5-72b
- Last updated: 2026-10-11
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Qwen1.5-72B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-72B leads 33.2 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 40.3% for Qwen1.5-72B.

## Snapshot

| | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 30.8 |
| Rank | 237 | 285 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 33.2% |
| BigCodeBench Complete | 49.6% | 40.3% |
| HumanEval+ | 65.9% | 59.1% |
| LMArena Coding | — | 1165 |
| MBPP+ | — | 61.6% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1148 |

## Math

- Codellama 70b Instruct: —
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |

## Knowledge

- Codellama 70b Instruct: —
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 992 | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1141 |

## Long Context

- Codellama 70b Instruct: —
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Codellama 70b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1057 | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |

## FAQ

### Is Codellama 70b Instruct better than Qwen1.5-72B?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.8 on the Noometry Index.

### Is Codellama 70b Instruct or Qwen1.5-72B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 31.9 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Qwen1.5-72B share?

7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen1.5-72B has 22.