# Llama 2-70B vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-70b-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Qwen2.5 72B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 72B Instruct leads 26.9 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 63.2% for Qwen2.5 72B Instruct.

## Snapshot

| | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.1 | 31.5 |
| Rank | 343 | 259 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Llama 2-70B: 30.8 (#281)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1079 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Llama 2-70B: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Llama 2-70B: 13.7 (#324)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1271 |
| DTBench | 41.6% | 62.9% |
| BIG-Bench Hard | 64.9% | 79.8% |
| Epoch Capabilities Index | 113.59 | 129.01 |
| ForecastBench | 51.4 | 57.5 |
| HellaSwag | 85.3% | 84.8% |
| PIQA | 82.8% | 82.6% |
| WinoGrande | 80.2% | 82.3% |
| LMCA | — | 13.4% |
| CommonsenseQA 2.0 | 50% | — |
| LAMBADA | 78.9% | — |

## Math

- Llama 2-70B: 7.5 (#320)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 8.1% |
| LMArena Math | 1091 | 1283 |
| MATH Level 5 | 3.3% | 63.2% |
| Omni-MATH | — | 33% |
| GSM8K | 69.6% | — |

## Knowledge

- Llama 2-70B: 7.4 (#305)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 26.3% | 49.1% |
| LMArena Expert | 1039 | 1245 |
| ARC (AI2) Challenge | 78.3% | 94.5% |
| MMLU | 69.9% | 85.3% |
| TriviaQA | 87.6% | 71.9% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| BoolQ | 88.6% | — |
| OpenBookQA | 60.2% | — |

## Multilingual

- Llama 2-70B: 27.9 (#269)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1045 | 1252 |
| LMArena Chinese | 994 | 1272 |
| LMArena French | 1089 | 1279 |
| LMArena German | 1041 | 1234 |
| LMArena Japanese | 927 | 1180 |
| LMArena Korean | 964 | 1188 |
| LMArena Russian | 1083 | 1264 |
| LMArena Spanish | 1142 | 1255 |

## Instruction Following

- Llama 2-70B: 55.1 (#273)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1071 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Llama 2-70B: 32.2 (#265)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1062 | 1282 |

## Writing & Preference

- Llama 2-70B: 32.5 (#274)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Llama 2-70B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1115 | 1269 |
| LMArena Creative Writing | 1075 | 1221 |
| LMArena Multi-Turn | 1088 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Llama 2-70B better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 24.1 on the Noometry Index.

### Is Llama 2-70B or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 32.8 versus 30.8 in the Noometry coding category.

### How many benchmarks do Llama 2-70B and Qwen2.5 72B Instruct share?

30 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Qwen2.5 72B Instruct has 43.