# Llama 3-8B vs Qwen-14B

> Qwen-14B is the stronger model overall, scoring 30.8 to 25.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-8b-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Llama 3-8B scores higher in 4 categories and Qwen-14B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 8.3.

## Snapshot

| | Llama 3-8B | Qwen-14B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.3 | 30.8 |
| Rank | 338 | 273 |
| Context | 8K | — |
| Input $/M | $0.14 | — |
| Output $/M | $0.14 | — |
| Weights | Open | Open |

## Coding

- Llama 3-8B: 30.5 (#285)
- Qwen-14B: 30.6 (#283)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1152 | 1072 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |

## Reasoning

- Llama 3-8B: 13.8 (#321)
- Qwen-14B: 18.7 (#255)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1027 |
| Epoch Capabilities Index | 116.33 | 112.8 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 58.6 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
| WinoGrande | 75.7% | — |

## Math

- Llama 3-8B: 8.3 (#317)
- Qwen-14B: 28.7 (#224)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Math | 1151 | 1068 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
| GSM8K | — | 61.3% |

## Knowledge

- Llama 3-8B: 7.8 (#303)
- Qwen-14B: —

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 82.8% | 84.4% |
| MMLU | 68.8% | 66.3% |
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| BoolQ | — | 86.2% |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |

## Multilingual

- Llama 3-8B: 31.0 (#256)
- Qwen-14B: 27.7 (#270)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1098 | 1042 |
| LMArena Chinese | 1076 | 1077 |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |

## Instruction Following

- Llama 3-8B: 58.7 (#255)
- Qwen-14B: 52.6 (#284)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1127 | 1031 |

## Long Context

- Llama 3-8B: 34.2 (#246)
- Qwen-14B: 31.3 (#276)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1128 | 1029 |

## Writing & Preference

- Llama 3-8B: 37.7 (#251)
- Qwen-14B: 27.8 (#294)

| Benchmark | Llama 3-8B | Qwen-14B |
|---|---|---|
| LMArena Text | 1166 | 1051 |
| LMArena Creative Writing | 1150 | 1028 |
| LMArena Multi-Turn | 1152 | 1022 |

## FAQ

### Is Llama 3-8B better than Qwen-14B?

Qwen-14B is the stronger model overall, scoring 30.8 to 25.3 on the Noometry Index.

### Is Llama 3-8B or Qwen-14B better for coding?

They score almost the same on coding (30.5 vs 30.6); test both on your own repository before choosing.

### How many benchmarks do Llama 3-8B and Qwen-14B share?

13 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen-14B has 18.