Model comparison
Claude 3.7 Sonnet vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 39.5 on the Noometry Index.
Last verified . 36 shared benchmarks.
Alibaba (Qwen)Summary
- They share 36 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 4 categories and Qwen3 235B-A22B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 37.5.
- The biggest single-benchmark swing is Omni-MATH: 33% for Claude 3.7 Sonnet and 71.8% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 43.5 |
| 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 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Claude 3.7 Sonnet: 40.6 (#136), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 64.9% | 59.6% |
| LMArena Coding | 1361 | 1445 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| SciCode | — | 42.4% |
| GSO | 3.8% | — |
| WeirdML | — | 41% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Too close to call
Claude 3.7 Sonnet: 34.1 (#50), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.6 (#277), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 0.9% | 1.3% |
| SimpleBench | 46.4% | 31% |
| ARC-AGI-1 | 28.6% | 11% |
| LMArena Hard Prompts | 1333 | 1433 |
| Epoch Capabilities Index | 141.16 | 143.85 |
| ForecastBench | 61.8 | 59.7 |
| Kagi LLM Benchmark | — | 69.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 29.3% |
| LiveBench | 76.1% | — |
Math Qwen3 235B-A22B leads
Claude 3.7 Sonnet: 37.5 (#153), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 86.7% |
| Omni-MATH | 33% | 71.8% |
| LMArena Math | 1337 | 1432 |
| MATH Level 5 | 91.2% | 68.9% |
| FrontierMath (Feb 2025 set) | 4.1% | 8.5% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Claude 3.7 Sonnet: 39.8 (#130), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 79.7% | 80.1% |
| MMLU-Pro | 78.4% | 84.4% |
| Confabulations | 14.7% | 15.6% |
| GPQA (HELM) | 60.8% | 72.7% |
| LMArena Expert | 1321 | 1463 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 40.4% |
| Vectara Hallucination Rate | — | 9.3% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Qwen3 235B-A22B: —
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Qwen3 235B-A22B leads
Claude 3.7 Sonnet: 44.1 (#179), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1296 | 1409 |
| LMArena Chinese | 1299 | 1481 |
| LMArena French | 1303 | 1445 |
| LMArena German | 1301 | 1433 |
| LMArena Japanese | 1267 | 1399 |
| LMArena Korean | 1249 | 1391 |
| LMArena Russian | 1311 | 1411 |
| LMArena Spanish | 1298 | 1430 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 72.9 (#125), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 83.4% | 83.5% |
| LMArena Instruction Following | 1352 | 1408 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | 83.3% | 75% |
| LMArena Longer Query | 1373 | 1426 |
Writing & Preference Qwen3 235B-A22B leads
Claude 3.7 Sonnet: 54.4 (#150), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Claude 3.7 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1314 | 1419 |
| LMArena Creative Writing | 1332 | 1384 |
| Short-Story Creative Writing | 81.1% | 83% |
| EQ-Bench Creative Writing | 1412 | 1366 |
| WildBench | 81.4% | 86.6% |
| LMArena Multi-Turn | 1339 | 1432 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Qwen3 235B-A22B share?
36 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3 235B-A22B has 49.