# Claude 3 Sonnet vs Qwen3-Coder 480B-A35B Instruct

> Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 34.9 to 10.0.
- The biggest single-benchmark swing is WeirdML: 10.2% for Claude 3 Sonnet and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.8 | 37.7 |
| Rank | 311 | 186 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 10.2% | 41.2% |
| LMArena Coding | 1223 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1213 | 1364 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1173 | 1337 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Qwen3-Coder 480B-A35B Instruct: —

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1205 | 1345 |
| LMArena Chinese | 1188 | 1356 |
| LMArena French | 1228 | 1394 |
| LMArena German | 1204 | 1324 |
| LMArena Japanese | 1131 | 1309 |
| LMArena Korean | 1128 | 1307 |
| LMArena Russian | 1227 | 1367 |
| LMArena Spanish | 1204 | 1360 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1200 | 1356 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1211 | 1379 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

| Benchmark | Claude 3 Sonnet | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1218 | 1356 |
| LMArena Creative Writing | 1186 | 1333 |
| LMArena Multi-Turn | 1227 | 1365 |

## FAQ

### Is Claude 3 Sonnet better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Qwen3-Coder 480B-A35B Instruct share?

18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.