Model comparison
Claude 3.7 Sonnet vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 39.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3.5 Max Preview leads 56.4 to 44.3.
Side by side
| Claude 3.7 Sonnet | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.4 | 44.7 |
| Released | 2025-02-24 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 41.1 (#120), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1361 | 1488 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 33.9 (#46), Qwen3.5 Max Preview: —
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 18.7 (#252), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1483 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 35.7 (#137), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1336 | 1473 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 39.7 (#117), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1321 | 1489 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), Qwen3.5 Max Preview: —
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 44.3 (#174), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1296 | 1465 |
| LMArena Chinese | 1299 | 1534 |
| LMArena French | 1302 | 1483 |
| LMArena German | 1301 | 1487 |
| LMArena Japanese | 1268 | 1497 |
| LMArena Korean | 1249 | 1438 |
| LMArena Russian | 1311 | 1472 |
| LMArena Spanish | 1299 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 73.1 (#120), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1352 | 1467 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1373 | 1477 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Qwen3.5 Max Preview leads
Claude 3.7 Sonnet: 54.6 (#145), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1314 | 1471 |
| LMArena Creative Writing | 1332 | 1464 |
| LMArena Multi-Turn | 1339 | 1478 |
| 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 Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 41.1 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3.5 Max Preview has 17.