# Llama 2-13B vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-13b-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where QwQ-32B leads 50.9 to 30.0.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Llama 2-13B and 5% for QwQ-32B.

## Snapshot

| | Llama 2-13B | QwQ-32B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 39.4 |
| Rank | 304 | 153 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 2-13B: 30.4 (#287)
- QwQ-32B: 34.9 (#220)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1062 | 1333 |
| Aider Polyglot | — | 20.9% |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |

## Reasoning

- Llama 2-13B: 12.3 (#333)
- QwQ-32B: 22.9 (#171)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1051 | 1326 |
| Epoch Capabilities Index | 105.8 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 42.2% | — |
| LiveBench Data Analysis | — | 65% |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 58.3 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| LiveBench | — | 72% |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |

## Math

- Llama 2-13B: 28.7 (#226)
- QwQ-32B: 36.2 (#123)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Math | 1065 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| GSM8K | 36.9% | — |

## Knowledge

- Llama 2-13B: 27.5 (#244)
- QwQ-32B: 37.2 (#150)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Expert | 1030 | 1323 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |

## Multimodal

- Llama 2-13B: —
- QwQ-32B: —

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| ScienceQA | 55.8% | — |

## Multilingual

- Llama 2-13B: 26.7 (#274)
- QwQ-32B: 45.0 (#171)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1024 | 1306 |
| LMArena Chinese | 1001 | 1378 |
| LMArena French | 1043 | 1337 |
| LMArena German | 1009 | 1313 |
| LMArena Japanese | 894 | 1263 |
| LMArena Korean | 953 | 1278 |
| LMArena Russian | 1055 | 1297 |
| LMArena Spanish | 1086 | 1353 |

## Instruction Following

- Llama 2-13B: 53.5 (#282)
- QwQ-32B: 72.8 (#131)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1046 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- Llama 2-13B: 32.3 (#264)
- QwQ-32B: 49.0 (#11)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1064 | 1308 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Llama 2-13B: 30.0 (#284)
- QwQ-32B: 50.9 (#175)

| Benchmark | Llama 2-13B | QwQ-32B |
|---|---|---|
| LMArena Text | 1085 | 1329 |
| LMArena Creative Writing | 1047 | 1288 |
| LMArena Multi-Turn | 1050 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |

## FAQ

### Is Llama 2-13B better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.

### Is Llama 2-13B or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 34.9 versus 30.4 in the Noometry coding category.

### How many benchmarks do Llama 2-13B and QwQ-32B share?

19 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and QwQ-32B has 36.