# Claude 3 Sonnet vs Qwen2-72B

> Claude 3 Sonnet and Qwen2-72B score almost the same on the Noometry Index (28.8 vs 29.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Qwen2-72B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 27.9 to 10.0.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.8 | 29.5 |
| Rank | 311 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| WeirdML | 10.2% | 11.3% |
| BigCodeBench Instruct | 42.7% | 38.5% |
| LMArena Coding | 1223 | 1196 |
| BigCodeBench Complete | 53.8% | 54% |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1191 |
| Epoch Capabilities Index | 120.69 | 125.27 |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Math | 1213 | 1235 |
| MATH Level 5 | 18.2% | 39.1% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 40.6% | 40.8% |
| LMArena Expert | 1173 | 1171 |
| MMLU | 75.9% | 82.4% |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Qwen2-72B: —

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1205 | 1176 |
| LMArena Chinese | 1188 | 1240 |
| LMArena French | 1228 | 1169 |
| LMArena German | 1204 | 1151 |
| LMArena Japanese | 1131 | 1111 |
| LMArena Korean | 1128 | 1083 |
| LMArena Russian | 1227 | 1169 |
| LMArena Spanish | 1204 | 1168 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1200 | 1181 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1211 | 1193 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Claude 3 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Text | 1218 | 1203 |
| LMArena Creative Writing | 1186 | 1181 |
| LMArena Multi-Turn | 1227 | 1195 |

## FAQ

### Is Claude 3 Sonnet better than Qwen2-72B?

Claude 3 Sonnet and Qwen2-72B score almost the same on the Noometry Index (28.8 vs 29.5), so choose on price, context window or the category you care about most.

### Is Claude 3 Sonnet or Qwen2-72B better for coding?

They score almost the same on coding (29.2 vs 28.7); test both on your own repository before choosing.

### How many benchmarks do Claude 3 Sonnet and Qwen2-72B share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen2-72B has 26.