# Qwen2.5-Coder-32B vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.4 to 32.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-coder-32b-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where QwQ-32B leads 34.9 to 22.4.
- The biggest single-benchmark swing is LiveBench Reasoning: 42.1% for Qwen2.5-Coder-32B and 83.5% for QwQ-32B.

## Snapshot

| | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 32.9 | 39.4 |
| Rank | 239 | 153 |
| Context | 33K | — |
| Input $/M | $0.66 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- Qwen2.5-Coder-32B: 22.4 (#328)
- QwQ-32B: 34.9 (#220)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| Aider Polyglot | 16.4% | 20.9% |
| BigCodeBench Instruct | 49% | 44.6% |
| LiveBench Coding | 56.9% | 72.2% |
| LMArena Coding | 1276 | 1333 |
| BigCodeBench Complete | 58% | 54.4% |
| SWE-bench Verified (bash only) | 9% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |

## Reasoning

- Qwen2.5-Coder-32B: 20.4 (#220)
- QwQ-32B: 22.9 (#171)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 42.1% | 83.5% |
| LMArena Hard Prompts | 1251 | 1326 |
| LiveBench Data Analysis | 49.9% | 65% |
| Epoch Capabilities Index | 119.41 | 137.6 |
| LiveBench | 46.2% | 72% |
| Chess Puzzles | — | 5% |
| ForecastBench | — | 58.3 |
| HellaSwag | 83% | — |
| WinoGrande | 80.8% | — |

## Math

- Qwen2.5-Coder-32B: 30.8 (#203)
- QwQ-32B: 36.2 (#123)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LiveBench Math | 46.6% | 77.8% |
| LMArena Math | 1251 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| GSM8K | 93% | — |

## Knowledge

- Qwen2.5-Coder-32B: 32.9 (#200)
- QwQ-32B: 37.2 (#150)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LMArena Expert | 1221 | 1323 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |

## Multilingual

- Qwen2.5-Coder-32B: 38.0 (#230)
- QwQ-32B: 45.0 (#171)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1205 | 1306 |
| LMArena Chinese | 1222 | 1378 |
| LMArena Russian | 1228 | 1297 |
| LMArena French | — | 1337 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
| LMArena Spanish | — | 1353 |

## Instruction Following

- Qwen2.5-Coder-32B: 61.6 (#240)
- QwQ-32B: 72.8 (#131)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 58.7% | 81.8% |
| LMArena Instruction Following | 1223 | 1297 |

## Long Context

- Qwen2.5-Coder-32B: 37.9 (#204)
- QwQ-32B: 49.0 (#11)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1251 | 1308 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Qwen2.5-Coder-32B: 41.8 (#235)
- QwQ-32B: 50.9 (#175)

| Benchmark | Qwen2.5-Coder-32B | QwQ-32B |
|---|---|---|
| LMArena Text | 1230 | 1329 |
| LMArena Creative Writing | 1174 | 1288 |
| LMArena Multi-Turn | 1222 | 1314 |
| LiveBench Language | 23.3% | 51.4% |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |

## FAQ

### Is Qwen2.5-Coder-32B better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 32.9 on the Noometry Index.

### Is Qwen2.5-Coder-32B or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 34.9 versus 22.4 in the Noometry coding category.

### How many benchmarks do Qwen2.5-Coder-32B and QwQ-32B share?

23 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and QwQ-32B has 36.