# Llama 2-13B vs Qwen2-72B

> Llama 2-13B and Qwen2-72B score almost the same on the Noometry Index (29.1 vs 29.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/llama-2-13b-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Llama 2-13B scores higher in 3 categories and Qwen2-72B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 41.0 to 30.0.

## Snapshot

| | Llama 2-13B | Qwen2-72B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 29.5 |
| Rank | 304 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 2-13B: 30.4 (#287)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1062 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Llama 2-13B: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Llama 2-13B: 12.3 (#333)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1191 |
| Epoch Capabilities Index | 105.8 | 125.27 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |

## Math

- Llama 2-13B: 28.7 (#226)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1065 | 1235 |
| MATH Level 5 | — | 39.1% |
| GSM8K | 36.9% | — |

## Knowledge

- Llama 2-13B: 27.5 (#244)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1030 | 1171 |
| MMLU | 55.6% | 82.4% |
| GPQA Diamond | — | 40.8% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |

## Multimodal

- Llama 2-13B: —
- Qwen2-72B: —

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| ScienceQA | 55.8% | — |

## Multilingual

- Llama 2-13B: 26.7 (#274)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1024 | 1176 |
| LMArena Chinese | 1001 | 1240 |
| LMArena French | 1043 | 1169 |
| LMArena German | 1009 | 1151 |
| LMArena Japanese | 894 | 1111 |
| LMArena Korean | 953 | 1083 |
| LMArena Russian | 1055 | 1169 |
| LMArena Spanish | 1086 | 1168 |

## Instruction Following

- Llama 2-13B: 53.5 (#282)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1046 | 1181 |

## Long Context

- Llama 2-13B: 32.3 (#264)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1064 | 1193 |

## Writing & Preference

- Llama 2-13B: 30.0 (#284)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Llama 2-13B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1085 | 1203 |
| LMArena Creative Writing | 1047 | 1181 |
| LMArena Multi-Turn | 1050 | 1195 |

## FAQ

### Is Llama 2-13B better than Qwen2-72B?

Llama 2-13B and Qwen2-72B score almost the same on the Noometry Index (29.1 vs 29.5), so choose on price, context window or the category you care about most.

### Is Llama 2-13B or Qwen2-72B better for coding?

Llama 2-13B scores higher on coding benchmarks: 30.4 versus 28.7 in the Noometry coding category.

### How many benchmarks do Llama 2-13B and Qwen2-72B share?

19 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen2-72B has 26.