Model comparison
Claude Sonnet 4.5 vs QwQ-32B
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 39.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and QwQ-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.7 to 50.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 59.2% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | QwQ-32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 44.0 | 39.4 |
| Released | 2025-09-29 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.8 (#54), QwQ-32B: 34.9 (#220)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1489 | 1333 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.1 (#30), QwQ-32B: —
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#113), QwQ-32B: 22.9 (#171)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 12% | 5% |
| LMArena Hard Prompts | 1462 | 1326 |
| Epoch Capabilities Index | 146.84 | 137.6 |
| ForecastBench | 61.9 | 58.3 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 83.5% |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 38.8% | — |
| LiveBench | — | 72% |
Math QwQ-32B leads
Claude Sonnet 4.5: 31.9 (#190), QwQ-32B: 36.2 (#123)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 59.2% |
| LMArena Math | 1448 | 1359 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#70), QwQ-32B: 37.2 (#150)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 82.3% | 65.3% |
| LMArena Expert | 1483 | 1323 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.1 (#84), QwQ-32B: —
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.6 (#65), QwQ-32B: 45.0 (#171)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1425 | 1306 |
| LMArena Chinese | 1459 | 1378 |
| LMArena French | 1459 | 1337 |
| LMArena German | 1427 | 1313 |
| LMArena Japanese | 1390 | 1263 |
| LMArena Korean | 1403 | 1278 |
| LMArena Russian | 1436 | 1297 |
| LMArena Spanish | 1457 | 1353 |
Instruction Following Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 75.2 (#74), QwQ-32B: 72.8 (#131)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1459 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 85% | — |
Long Context QwQ-32B leads
Claude Sonnet 4.5: 45.2 (#45), QwQ-32B: 49.0 (#11)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1476 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.7 (#33), QwQ-32B: 50.9 (#175)
| Benchmark | Claude Sonnet 4.5 | QwQ-32B |
|---|---|---|
| LMArena Text | 1439 | 1329 |
| LMArena Creative Writing | 1442 | 1288 |
| EQ-Bench Creative Writing | 1678 | 1257 |
| LMArena Multi-Turn | 1465 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| WildBench | 85.4% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Claude Sonnet 4.5 better than QwQ-32B?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 39.4 on the Noometry Index.
Is Claude Sonnet 4.5 or QwQ-32B better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 34.9 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and QwQ-32B share?
23 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and QwQ-32B has 36.