# Llama 2-34B vs Llama 2-7B

> Llama 2-7B has enough public results to be ranked (#317); Llama 2-34B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-2-34b-vs-llama-2-7b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both.
- Llama 2-7B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 2-34B | Llama 2-7B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | — | 29.1 |
| Rank | — | 317 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Llama 2-34B: —
- Llama 2-7B: 29.2 (#307)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| LMArena Coding | — | 1002 |

## Reasoning

- Llama 2-34B: —
- Llama 2-7B: 15.7 (#312)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| BIG-Bench Hard | 44.1% | 39.2% |
| Epoch Capabilities Index | 105.2 | 99.06 |
| PIQA | 81.9% | 78.8% |
| WinoGrande | 76.7% | 69.2% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1009 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |

## Math

- Llama 2-34B: —
- Llama 2-7B: 30.7 (#233)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| GSM8K | 42.2% | 16.7% |
| LMArena Math | — | 1042 |

## Knowledge

- Llama 2-34B: —
- Llama 2-7B: 28.2 (#248)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 45.9% |
| BoolQ | 83.7% | 77.9% |
| MMLU | 62.6% | 45.8% |
| OpenBookQA | 58.2% | 58.6% |
| TriviaQA | 84.6% | 73.7% |
| LMArena Expert | — | 1036 |

## Multimodal

- Llama 2-34B: —
- Llama 2-7B: —

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |

## Multilingual

- Llama 2-34B: —
- Llama 2-7B: 23.8 (#293)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| LMArena Non-English | — | 973 |
| LMArena Chinese | — | 973 |
| LMArena French | — | 970 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |

## Instruction Following

- Llama 2-34B: —
- Llama 2-7B: 50.8 (#298)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | — | 1006 |

## Long Context

- Llama 2-34B: —
- Llama 2-7B: 30.4 (#287)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | — | 999 |

## Writing & Preference

- Llama 2-34B: —
- Llama 2-7B: 28.0 (#298)

| Benchmark | Llama 2-34B | Llama 2-7B |
|---|---|---|
| LMArena Text | — | 1053 |
| LMArena Creative Writing | — | 1033 |
| LMArena Multi-Turn | — | 1029 |

## FAQ

### Is Llama 2-34B better than Llama 2-7B?

Llama 2-7B has enough public results to be ranked (#317); Llama 2-34B does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 2-34B and Llama 2-7B share?

10 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Llama 2-7B has 29.