# Llama 2-7B vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-7b-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Llama 2-7B scores higher in 2 categories and Qwen2.5 72B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 28.1.

## Snapshot

| | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.6 | 31.5 |
| Rank | 315 | 259 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Llama 2-7B: 28.7 (#302)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1002 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Llama 2-7B: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Llama 2-7B: 15.1 (#309)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1271 |
| BIG-Bench Hard | 39.2% | 79.8% |
| Epoch Capabilities Index | 98.54 | 129.01 |
| HellaSwag | 77.2% | 84.8% |
| PIQA | 78.8% | 82.6% |
| WinoGrande | 69.2% | 82.3% |
| Chess Puzzles | 0% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| ForecastBench | — | 57.5 |
| LAMBADA | 73.3% | — |

## Math

- Llama 2-7B: 28.2 (#231)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1042 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
| GSM8K | 16.7% | — |

## Knowledge

- Llama 2-7B: 27.7 (#243)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1036 | 1245 |
| ARC (AI2) Challenge | 45.9% | 94.5% |
| MMLU | 45.8% | 85.3% |
| TriviaQA | 73.7% | 71.9% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| BoolQ | 77.9% | — |
| OpenBookQA | 58.6% | — |

## Multimodal

- Llama 2-7B: —
- Qwen2.5 72B Instruct: —

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| ScienceQA | 43.1% | — |

## Multilingual

- Llama 2-7B: 23.9 (#288)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 973 | 1252 |
| LMArena Chinese | 973 | 1272 |
| LMArena French | 969 | 1279 |
| LMArena German | 978 | 1234 |
| LMArena Russian | 995 | 1264 |
| LMArena Spanish | 1007 | 1255 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |

## Instruction Following

- Llama 2-7B: 51.0 (#293)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1006 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Llama 2-7B: 30.4 (#282)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 999 | 1282 |

## Writing & Preference

- Llama 2-7B: 28.1 (#293)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Llama 2-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1053 | 1269 |
| LMArena Creative Writing | 1033 | 1221 |
| LMArena Multi-Turn | 1029 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Llama 2-7B better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 28.6 on the Noometry Index.

### Is Llama 2-7B or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 32.8 versus 28.7 in the Noometry coding category.

### How many benchmarks do Llama 2-7B and Qwen2.5 72B Instruct share?

23 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Qwen2.5 72B Instruct has 43.