Model comparison
Claude 3.7 Sonnet vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Qwen3.5 35B-A3B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 39.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 42.0 |
| Released | 2025-02-24 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 58 | 28 |
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: 40.6 (#136), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1361 | 1410 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 34.1 (#50), Qwen3.5 35B-A3B: —
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Qwen3.5 35B-A3B leads
Claude 3.7 Sonnet: 18.6 (#277), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1400 |
| Epoch Capabilities Index | 141.16 | 142.52 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 80% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 29.5% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Qwen3.5 35B-A3B leads
Claude 3.7 Sonnet: 37.5 (#153), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 70% |
| LMArena Math | 1337 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Qwen3.5 35B-A3B leads
Claude 3.7 Sonnet: 39.8 (#130), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 79.7% | 83.5% |
| LMArena Expert | 1321 | 1408 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Qwen3.5 35B-A3B: —
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Qwen3.5 35B-A3B leads
Claude 3.7 Sonnet: 44.1 (#179), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1296 | 1378 |
| LMArena Chinese | 1299 | 1457 |
| LMArena French | 1303 | 1412 |
| LMArena German | 1301 | 1367 |
| LMArena Japanese | 1267 | 1325 |
| LMArena Korean | 1249 | 1356 |
| LMArena Russian | 1311 | 1376 |
| LMArena Spanish | 1298 | 1392 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 72.9 (#125), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1379 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1373 | 1389 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Qwen3.5 35B-A3B leads
Claude 3.7 Sonnet: 54.4 (#150), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Claude 3.7 Sonnet | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1314 | 1395 |
| LMArena Creative Writing | 1332 | 1346 |
| LMArena Multi-Turn | 1339 | 1390 |
| 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 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Qwen3.5 35B-A3B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 33.8 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Qwen3.5 35B-A3B share?
20 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3.5 35B-A3B has 28.