# Llama 2-34B vs Qwen-14B

> Qwen-14B has enough public results to be ranked (#273); Llama 2-34B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-2-34b-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both.
- Qwen-14B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 2-34B | Qwen-14B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | — | 30.8 |
| Rank | — | 273 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Llama 2-34B: —
- Qwen-14B: 30.6 (#283)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| LMArena Coding | — | 1072 |

## Reasoning

- Llama 2-34B: —
- Qwen-14B: 18.7 (#255)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| BIG-Bench Hard | 44.1% | 55% |
| Epoch Capabilities Index | 104.81 | 112.8 |
| PIQA | 81.9% | 79.9% |
| LMArena Hard Prompts | — | 1027 |
| LAMBADA | — | 71.1% |
| WinoGrande | 76.7% | — |

## Math

- Llama 2-34B: —
- Qwen-14B: 28.7 (#224)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| GSM8K | 42.2% | 61.3% |
| LMArena Math | — | 1068 |

## Knowledge

- Llama 2-34B: —
- Qwen-14B: —

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 84.4% |
| BoolQ | 83.7% | 86.2% |
| MMLU | 62.6% | 66.3% |
| OpenBookQA | 58.2% | — |
| TriviaQA | 84.6% | — |

## Multilingual

- Llama 2-34B: —
- Qwen-14B: 27.7 (#270)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |

## Instruction Following

- Llama 2-34B: —
- Qwen-14B: 52.6 (#284)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |

## Long Context

- Llama 2-34B: —
- Qwen-14B: 31.3 (#276)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |

## Writing & Preference

- Llama 2-34B: —
- Qwen-14B: 27.8 (#294)

| Benchmark | Llama 2-34B | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |

## FAQ

### Is Llama 2-34B better than Qwen-14B?

Qwen-14B has enough public results to be ranked (#273); Llama 2-34B does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 2-34B and Qwen-14B share?

7 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Qwen-14B has 18.