Model comparison
Claude 3.7 Sonnet vs QwQ-32B
Claude 3.7 Sonnet and QwQ-32B score almost the same on the Noometry Index (39.4 vs 39.4), so choose on price, context window or the category you care about most.
Last verified . 33 shared benchmarks.
Alibaba (Qwen)Summary
- They share 33 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 5 categories and QwQ-32B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude 3.7 Sonnet leads 41.1 to 34.9.
- The biggest single-benchmark swing is Aider Polyglot: 64.9% for Claude 3.7 Sonnet and 20.9% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | QwQ-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.4 | 39.4 |
| Released | 2025-02-24 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), QwQ-32B: 34.9 (#220)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| Aider Polyglot | 64.9% | 20.9% |
| LiveBench Coding | 74.5% | 72.2% |
| LMArena Coding | 1361 | 1333 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| GSO | 3.8% | — |
| BigCodeBench Instruct | — | 44.6% |
| BigCodeBench Complete | — | 54.4% |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 33.9 (#46), QwQ-32B: —
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning QwQ-32B leads
Claude 3.7 Sonnet: 18.7 (#252), QwQ-32B: 22.9 (#171)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 87.8% | 83.5% |
| LMArena Hard Prompts | 1333 | 1326 |
| LiveBench Data Analysis | 74% | 65% |
| Epoch Capabilities Index | 141.16 | 137.6 |
| ForecastBench | 61.8 | 58.3 |
| LiveBench | 76.1% | 72% |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 4.2% | — |
Math Too close to call
Claude 3.7 Sonnet: 35.7 (#137), QwQ-32B: 36.2 (#123)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 59.2% |
| LiveBench Math | 79% | 77.8% |
| LMArena Math | 1336 | 1359 |
| Omni-MATH | 33% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), QwQ-32B: 37.2 (#150)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| GPQA Diamond | 79.7% | 65.3% |
| Confabulations | 14.7% | 15.6% |
| LMArena Expert | 1321 | 1323 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), QwQ-32B: —
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Too close to call
Claude 3.7 Sonnet: 44.3 (#174), QwQ-32B: 45.0 (#171)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1296 | 1306 |
| LMArena Chinese | 1299 | 1378 |
| LMArena French | 1302 | 1337 |
| LMArena German | 1301 | 1313 |
| LMArena Japanese | 1268 | 1263 |
| LMArena Korean | 1249 | 1278 |
| LMArena Russian | 1311 | 1297 |
| LMArena Spanish | 1299 | 1353 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 73.1 (#120), QwQ-32B: 72.8 (#131)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 81.8% |
| LMArena Instruction Following | 1352 | 1297 |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), QwQ-32B: 49.0 (#11)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 83.3% | 83.3% |
| LMArena Longer Query | 1373 | 1308 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), QwQ-32B: 50.9 (#175)
| Benchmark | Claude 3.7 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Text | 1314 | 1329 |
| LMArena Creative Writing | 1332 | 1288 |
| Short-Story Creative Writing | 81.1% | 80.2% |
| EQ-Bench Creative Writing | 1412 | 1257 |
| LMArena Multi-Turn | 1339 | 1314 |
| LiveBench Language | 59.9% | 51.4% |
| WildBench | 81.4% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than QwQ-32B?
Claude 3.7 Sonnet and QwQ-32B score almost the same on the Noometry Index (39.4 vs 39.4), so choose on price, context window or the category you care about most.
Is Claude 3.7 Sonnet or QwQ-32B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 34.9 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and QwQ-32B share?
33 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and QwQ-32B has 36.