# Claude 3 Sonnet vs Qwen-14B

> Qwen-14B is the stronger model overall, scoring 30.8 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 10.0.
- Qwen-14B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.8 | 30.8 |
| Rank | 311 | 273 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Qwen-14B: 30.6 (#283)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Coding | 1223 | 1072 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Qwen-14B: 18.7 (#255)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1027 |
| Epoch Capabilities Index | 120.69 | 112.8 |
| DTBench | 53.6% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Qwen-14B: 28.7 (#224)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Math | 1213 | 1068 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
| GSM8K | — | 61.3% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Qwen-14B: —

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| MMLU | 75.9% | 66.3% |
| GPQA Diamond | 40.6% | — |
| LMArena Expert | 1173 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Qwen-14B: —

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Qwen-14B: 27.7 (#270)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1205 | 1042 |
| LMArena Chinese | 1188 | 1077 |
| LMArena French | 1228 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Qwen-14B: 52.6 (#284)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1200 | 1031 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Qwen-14B: 31.3 (#276)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1211 | 1029 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Qwen-14B: 27.8 (#294)

| Benchmark | Claude 3 Sonnet | Qwen-14B |
|---|---|---|
| LMArena Text | 1218 | 1051 |
| LMArena Creative Writing | 1186 | 1028 |
| LMArena Multi-Turn | 1227 | 1022 |

## FAQ

### Is Claude 3 Sonnet better than Qwen-14B?

Qwen-14B is the stronger model overall, scoring 30.8 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Qwen-14B better for coding?

Qwen-14B scores higher on coding benchmarks: 30.6 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Qwen-14B share?

12 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen-14B has 18.