# Codellama 70b Instruct vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-qwq-32b
- 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 QwQ-32B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where QwQ-32B leads 72.6 to 51.9.

## Snapshot

| | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 39.8 |
| Rank | 237 | 159 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- QwQ-32B: 35.4 (#226)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 44.6% |
| BigCodeBench Complete | 49.6% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- QwQ-32B: 23.7 (#174)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1325 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- Codellama 70b Instruct: —
- QwQ-32B: 38.0 (#143)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |

## Knowledge

- Codellama 70b Instruct: —
- QwQ-32B: 37.2 (#158)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1324 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- QwQ-32B: 44.8 (#176)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| LMArena Non-English | 992 | 1305 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1336 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1354 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- QwQ-32B: 72.6 (#137)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- Codellama 70b Instruct: —
- QwQ-32B: 49.0 (#11)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1308 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- QwQ-32B: 50.6 (#180)

| Benchmark | Codellama 70b Instruct | QwQ-32B |
|---|---|---|
| LMArena Text | 1057 | 1329 |
| LMArena Creative Writing | — | 1288 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 51.4% |

## FAQ

### Is Codellama 70b Instruct better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or QwQ-32B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 35.4 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and QwQ-32B share?

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and QwQ-32B has 36.