Model comparison
Claude Sonnet 4 vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 40.6 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Claude Sonnet 4 scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 48.4 to 23.0.
- The biggest single-benchmark swing is SimpleBench: 45.5% for Claude Sonnet 4 and 70.4% for Qwen3.7 Max.
- Qwen3.7 Max is cheaper at $2.50 / $7.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Qwen3.7 Max accepts more context: 1M tokens versus 200K.
Side by side
| Claude Sonnet 4 | Qwen3.7 Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.6 | 51.4 |
| Released | 2025-05-22 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $2.50 |
| Output $ / M tokens | $15 | $7.50 |
| Results tracked | 58 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Claude Sonnet 4: 44.0 (#70), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| SciCode | 40% | 48.8% |
| LMArena Coding | 1414 | 1498 |
| ALE-Bench | 655.35 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1515 |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.3 (#29), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| GBAEval | — | 0.4% |
| METR Time Horizons | 62% | — |
Reasoning Qwen3.7 Max leads
Claude Sonnet 4: 23.0 (#169), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 45.5% | 70.4% |
| CritPt | 0.3% | 13.4% |
| LMArena Hard Prompts | 1372 | 1483 |
| DTBench | 77.1% | 92.3% |
| LMCA | 29% | 44% |
| Epoch Capabilities Index | 141.69 | 153.74 |
| ARC-AGI-2 | 5.9% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 40% | — |
| Chess Puzzles | — | 19% |
| EnigmaEval | 3.1% | — |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| ForecastBench | 60.2 | — |
Math Qwen3.7 Max leads
Claude Sonnet 4: 41.5 (#71), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 95.6% |
| LMArena Math | 1375 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.7 Max leads
Claude Sonnet 4: 41.6 (#99), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 79.2% | 90.9% |
| LMArena Expert | 1371 | 1488 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), Qwen3.7 Max: —
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Qwen3.7 Max leads
Claude Sonnet 4: 46.9 (#151), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1333 | 1475 |
| LMArena Chinese | 1351 | 1533 |
| LMArena Russian | 1355 | 1482 |
| LMArena French | 1364 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1301 | — |
| LMArena Korean | 1293 | — |
| LMArena Spanish | 1356 | — |
Instruction Following Qwen3.7 Max leads
Claude Sonnet 4: 71.8 (#141), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1375 | 1460 |
| IFEval | 84% | — |
Long Context Qwen3.7 Max leads
Claude Sonnet 4: 33.6 (#254), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1398 | 1484 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Qwen3.7 Max leads
Claude Sonnet 4: 57.3 (#127), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Claude Sonnet 4 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1351 | 1476 |
| LMArena Creative Writing | 1345 | 1450 |
| LMArena Multi-Turn | 1376 | 1482 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Claude Sonnet 4 better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Qwen3.7 Max?
Qwen3.7 Max is cheaper. It lists at $2.50 per million input tokens and $7.50 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Qwen3.7 Max share?
21 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen3.7 Max has 33.