# Claude 3 Sonnet vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Qwen2.5-Coder-32B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Coder-32B leads 33.3 to 10.7.
- The biggest single-benchmark swing is BigCodeBench Instruct: 42.7% for Claude 3 Sonnet and 49% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 29.0 | 33.4 |
| Rank | 319 | 245 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 49% |
| LMArena Coding | 1223 | 1276 |
| BigCodeBench Complete | 53.8% | 58% |
| HumanEval+ | 64% | 87.2% |
| MBPP+ | 69.3% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| WeirdML | 10.2% | — |
| LiveBench Coding | — | 56.9% |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1251 |
| Epoch Capabilities Index | 120.7 | 119.49 |
| WinoGrande | 75.1% | 80.8% |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 53.6% | — |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1213 | 1251 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 18.2% | — |
| GSM8K | — | 93% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1173 | 1221 |
| MMLU | 75.9% | 79.1% |
| GPQA Diamond | 40.6% | — |
| ARC (AI2) Challenge | — | 70.5% |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- Qwen2.5-Coder-32B: —

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1205 | 1205 |
| LMArena Chinese | 1189 | 1222 |
| LMArena Russian | 1227 | 1228 |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1211 | 1251 |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Claude 3 Sonnet | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1218 | 1230 |
| LMArena Creative Writing | 1186 | 1174 |
| LMArena Multi-Turn | 1227 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Claude 3 Sonnet better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.0 on the Noometry Index.

### Is Claude 3 Sonnet or Qwen2.5-Coder-32B better for coding?

Claude 3 Sonnet scores higher on coding benchmarks: 29.6 versus 22.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Qwen2.5-Coder-32B share?

19 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen2.5-Coder-32B has 31.