Model comparison
Claude 3.5 Sonnet vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 34.6 on the Noometry Index.
Last verified . 34 shared benchmarks.
Alibaba (Qwen)Summary
- They share 34 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and QwQ-32B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 38.0 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 59.2% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | QwQ-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 34.6 | 39.8 |
| Released | 2024-06-20 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), QwQ-32B: 35.4 (#226)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| Aider Polyglot | 51.6% | 20.9% |
| BigCodeBench Instruct | 46.8% | 44.6% |
| LiveBench Coding | 67.1% | 72.2% |
| LMArena Coding | 1342 | 1333 |
| BigCodeBench Complete | 58.6% | 54.4% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), QwQ-32B: —
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Too close to call
Claude 3.5 Sonnet: 23.1 (#183), QwQ-32B: 23.7 (#174)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 56.7% | 83.5% |
| LMArena Hard Prompts | 1305 | 1325 |
| LiveBench Data Analysis | 55% | 65% |
| Epoch Capabilities Index | 133.55 | 137.6 |
| ForecastBench | 60.7 | 58.3 |
| LiveBench | 59% | 72% |
| SimpleBench | 41.4% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 0.9% | — |
| DTBench | 67.8% | — |
Math QwQ-32B leads
Claude 3.5 Sonnet: 19.2 (#288), QwQ-32B: 38.0 (#143)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 59.2% |
| LiveBench Math | 52.3% | 77.8% |
| LMArena Math | 1307 | 1359 |
| Omni-MATH | 27.6% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge QwQ-32B leads
Claude 3.5 Sonnet: 28.6 (#245), QwQ-32B: 37.2 (#158)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| GPQA Diamond | 55.3% | 65.3% |
| Confabulations | 19.9% | 15.6% |
| LMArena Expert | 1265 | 1324 |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), QwQ-32B: —
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual QwQ-32B leads
Claude 3.5 Sonnet: 43.2 (#185), QwQ-32B: 44.8 (#176)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1283 | 1305 |
| LMArena Chinese | 1272 | 1378 |
| LMArena French | 1305 | 1336 |
| LMArena German | 1297 | 1313 |
| LMArena Japanese | 1234 | 1262 |
| LMArena Korean | 1200 | 1279 |
| LMArena Russian | 1306 | 1297 |
| LMArena Spanish | 1290 | 1354 |
Instruction Following QwQ-32B leads
Claude 3.5 Sonnet: 68.8 (#182), QwQ-32B: 72.6 (#137)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 81.8% |
| LMArena Instruction Following | 1297 | 1297 |
| IFEval | 85.5% | — |
Long Context QwQ-32B leads
Claude 3.5 Sonnet: 39.9 (#167), QwQ-32B: 49.0 (#11)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1311 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), QwQ-32B: 50.6 (#180)
| Benchmark | Claude 3.5 Sonnet | QwQ-32B |
|---|---|---|
| LMArena Text | 1298 | 1329 |
| LMArena Creative Writing | 1292 | 1288 |
| Short-Story Creative Writing | 80.3% | 80.2% |
| EQ-Bench Creative Writing | 1451 | 1257 |
| LMArena Multi-Turn | 1326 | 1314 |
| LiveBench Language | 53.8% | 51.4% |
| WildBench | 79.2% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or QwQ-32B better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 35.4 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and QwQ-32B share?
34 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and QwQ-32B has 36.