Model comparison
Claude Sonnet 4 vs QwQ-32B
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 39.4 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and QwQ-32B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 33.6.
- The biggest single-benchmark swing is Aider Polyglot: 61.3% for Claude Sonnet 4 and 20.9% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | QwQ-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.6 | 39.4 |
| Released | 2025-05-22 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), QwQ-32B: 34.9 (#220)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| Aider Polyglot | 61.3% | 20.9% |
| LMArena Coding | 1414 | 1333 |
| SWE-bench Verified (bash only) | 64.9% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.3 (#29), QwQ-32B: —
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Too close to call
Claude Sonnet 4: 23.0 (#169), QwQ-32B: 22.9 (#171)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1326 |
| Epoch Capabilities Index | 141.69 | 137.6 |
| ForecastBench | 60.2 | 58.3 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 77.1% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 29% | — |
| LiveBench | — | 72% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 41.5 (#71), QwQ-32B: 36.2 (#123)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 59.2% |
| LMArena Math | 1375 | 1359 |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.6 (#99), QwQ-32B: 37.2 (#150)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 79.2% | 65.3% |
| Confabulations | 13.2% | 15.6% |
| LMArena Expert | 1371 | 1323 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), QwQ-32B: —
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.9 (#151), QwQ-32B: 45.0 (#171)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1333 | 1306 |
| LMArena Chinese | 1351 | 1378 |
| LMArena French | 1364 | 1337 |
| LMArena German | 1331 | 1313 |
| LMArena Japanese | 1301 | 1263 |
| LMArena Korean | 1293 | 1278 |
| LMArena Russian | 1355 | 1297 |
| LMArena Spanish | 1356 | 1353 |
Instruction Following Too close to call
Claude Sonnet 4: 71.8 (#141), QwQ-32B: 72.8 (#131)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1375 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 84% | — |
Long Context QwQ-32B leads
Claude Sonnet 4: 33.6 (#254), QwQ-32B: 49.0 (#11)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 46.9% | 83.3% |
| LMArena Longer Query | 1398 | 1308 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.3 (#127), QwQ-32B: 50.9 (#175)
| Benchmark | Claude Sonnet 4 | QwQ-32B |
|---|---|---|
| LMArena Text | 1351 | 1329 |
| LMArena Creative Writing | 1345 | 1288 |
| Short-Story Creative Writing | 81.4% | 80.2% |
| EQ-Bench Creative Writing | 1483 | 1257 |
| LMArena Multi-Turn | 1376 | 1314 |
| WildBench | 83.8% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Claude Sonnet 4 better than QwQ-32B?
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 39.4 on the Noometry Index.
Is Claude Sonnet 4 or QwQ-32B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 34.9 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and QwQ-32B share?
26 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and QwQ-32B has 36.