Model comparison
Claude 3 Sonnet vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Qwen1.5-32B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 30.5 to 10.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet and 42% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Qwen1.5-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.8 | 30.0 |
| Released | 2024-02-29 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Claude 3 Sonnet: 29.2 (#296), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 32.3% |
| LMArena Coding | 1223 | 1155 |
| BigCodeBench Complete | 53.8% | 42% |
| WeirdML | 10.2% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Qwen1.5-32B leads
Claude 3 Sonnet: 19.7 (#232), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1131 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |
Math Qwen1.5-32B leads
Claude 3 Sonnet: 10.0 (#305), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1213 | 1155 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#271), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 40.6% | 30.7% |
| LMArena Expert | 1173 | 1126 |
| MMLU | 75.9% | 74.4% |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Qwen1.5-32B: —
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 38.0 (#229), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1205 | 1106 |
| LMArena Chinese | 1188 | 1176 |
| LMArena French | 1228 | 1100 |
| LMArena German | 1204 | 1058 |
| LMArena Japanese | 1131 | 1027 |
| LMArena Korean | 1128 | 1007 |
| LMArena Russian | 1227 | 1073 |
| LMArena Spanish | 1204 | 1089 |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 63.1 (#230), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1200 | 1116 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#223), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1211 | 1146 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.3 (#233), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Claude 3 Sonnet | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1218 | 1137 |
| LMArena Creative Writing | 1186 | 1083 |
| LMArena Multi-Turn | 1227 | 1140 |
Frequently asked questions
Is Claude 3 Sonnet better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.8 on the Noometry Index.
Is Claude 3 Sonnet or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 29.2 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Qwen1.5-32B share?
21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen1.5-32B has 21.