Model comparison
Claude Sonnet 4 vs Qwen1.5-32B
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 30.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4 leads 41.8 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 79.2% for Claude Sonnet 4 and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Qwen1.5-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.8 | 30.5 |
| Released | 2025-05-22 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1414 | 1155 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Qwen1.5-32B: —
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1130 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1375 | 1155 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 79.2% | 30.7% |
| LMArena Expert | 1372 | 1126 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Qwen1.5-32B: —
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1333 | 1106 |
| LMArena Chinese | 1350 | 1177 |
| LMArena French | 1363 | 1101 |
| LMArena German | 1331 | 1058 |
| LMArena Japanese | 1302 | 1027 |
| LMArena Korean | 1291 | 1008 |
| LMArena Russian | 1355 | 1073 |
| LMArena Spanish | 1357 | 1089 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1116 |
| IFEval | 84% | — |
Long Context Qwen1.5-32B leads
Claude Sonnet 4: 33.7 (#259), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1398 | 1146 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Claude Sonnet 4 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1351 | 1137 |
| LMArena Creative Writing | 1345 | 1083 |
| LMArena Multi-Turn | 1376 | 1140 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Qwen1.5-32B?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 30.5 on the Noometry Index.
Is Claude Sonnet 4 or Qwen1.5-32B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 31.7 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Qwen1.5-32B share?
18 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen1.5-32B has 21.