Model comparison
Claude 3.7 Sonnet vs Qwen3 32B
Claude 3.7 Sonnet and Qwen3 32B score almost the same on the Noometry Index (39.4 vs 38.8), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 5 categories and Qwen3 32B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.2 to 43.7.
- The biggest single-benchmark swing is Aider Polyglot: 64.9% for Claude 3.7 Sonnet and 40% for Qwen3 32B.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Qwen3 32B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.4 | 38.8 |
| Released | 2025-02-24 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 58 | 26 |
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), Qwen3 32B: 37.3 (#184)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| Aider Polyglot | 64.9% | 40% |
| LMArena Coding | 1361 | 1358 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| SciCode | — | 35.4% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), Qwen3 32B: 32.3 (#58)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Too close to call
Claude 3.7 Sonnet: 18.7 (#252), Qwen3 32B: 19.6 (#233)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1335 |
| Epoch Capabilities Index | 141.16 | 138.51 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 54.9% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 67.5% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 17.3% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Qwen3 32B leads
Claude 3.7 Sonnet: 35.7 (#137), Qwen3 32B: 37.9 (#89)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 66.9% |
| LMArena Math | 1336 | 1399 |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Too close to call
Claude 3.7 Sonnet: 39.7 (#117), Qwen3 32B: 40.0 (#112)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 79.7% | 65.7% |
| LMArena Expert | 1321 | 1362 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), Qwen3 32B: —
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Qwen3 32B leads
Claude 3.7 Sonnet: 44.3 (#174), Qwen3 32B: 45.8 (#162)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1296 | 1317 |
| LMArena Chinese | 1299 | 1357 |
| LMArena German | 1301 | 1341 |
| LMArena Russian | 1311 | 1311 |
| LMArena French | 1302 | — |
| LMArena Japanese | 1268 | — |
| LMArena Korean | 1249 | — |
| LMArena Spanish | 1299 | — |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 73.1 (#120), Qwen3 32B: 69.1 (#174)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1305 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Qwen3 32B: 43.7 (#83)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | 83.3% | 74.2% |
| LMArena Longer Query | 1373 | 1327 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), Qwen3 32B: 53.1 (#158)
| Benchmark | Claude 3.7 Sonnet | Qwen3 32B |
|---|---|---|
| LMArena Text | 1314 | 1340 |
| LMArena Creative Writing | 1332 | 1297 |
| LMArena Multi-Turn | 1339 | 1331 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Qwen3 32B?
Claude 3.7 Sonnet and Qwen3 32B score almost the same on the Noometry Index (39.4 vs 38.8), so choose on price, context window or the category you care about most.
Is Claude 3.7 Sonnet or Qwen3 32B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 37.3 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Qwen3 32B share?
18 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3 32B has 26.