# Qwen2.5 7B Instruct vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.4 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-7b-instruct-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 1 category and QwQ-32B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 36.2 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 59.2% for QwQ-32B.

## Snapshot

| | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 28.6 | 39.4 |
| Rank | 314 | 153 |
| Context | 131K | — |
| Input $/M | $0.17 | — |
| Output $/M | $0.70 | — |
| Weights | Open | Open |

## Coding

- Qwen2.5 7B Instruct: 35.9 (#204)
- QwQ-32B: 34.9 (#220)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 44.6% |
| BigCodeBench Complete | 46.1% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |

## Agentic & Tool Use

- Qwen2.5 7B Instruct: 23.5 (#117)
- QwQ-32B: —

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| BALROG | 7.8% | — |

## Reasoning

- Qwen2.5 7B Instruct: 14.3 (#317)
- QwQ-32B: 22.9 (#171)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| Epoch Capabilities Index | 118.44 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| LMArena Hard Prompts | — | 1326 |
| DTBench | 47.7% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 6.4% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- Qwen2.5 7B Instruct: 11.8 (#300)
- QwQ-32B: 36.2 (#123)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 59.2% |
| Omni-MATH | 29.4% | — |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |

## Knowledge

- Qwen2.5 7B Instruct: 17.0 (#281)
- QwQ-32B: 37.2 (#150)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| GPQA Diamond | 35.5% | 65.3% |
| MMLU-Pro | 53.9% | — |
| Confabulations | — | 15.6% |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1323 |
| MMLU | 72.9% | — |

## Multilingual

- Qwen2.5 7B Instruct: —
- QwQ-32B: 45.0 (#171)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| LMArena Non-English | — | 1306 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1337 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1353 |

## Instruction Following

- Qwen2.5 7B Instruct: 63.4 (#226)
- QwQ-32B: 72.8 (#131)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1297 |

## Long Context

- Qwen2.5 7B Instruct: —
- QwQ-32B: 49.0 (#11)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1308 |

## Writing & Preference

- Qwen2.5 7B Instruct: 48.8 (#194)
- QwQ-32B: 50.9 (#175)

| Benchmark | Qwen2.5 7B Instruct | QwQ-32B |
|---|---|---|
| LMArena Text | — | 1329 |
| LMArena Creative Writing | — | 1288 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 51.4% |

## FAQ

### Is Qwen2.5 7B Instruct better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 28.6 on the Noometry Index.

### Is Qwen2.5 7B Instruct or QwQ-32B better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 34.9 in the Noometry coding category.

### How many benchmarks do Qwen2.5 7B Instruct and QwQ-32B share?

6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and QwQ-32B has 36.