Model comparison
Claude Sonnet 4 vs Qwen2.5-Max
Claude Sonnet 4 and Qwen2.5-Max score almost the same on the Noometry Index (40.8 vs 40.7), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude Sonnet 4 scores higher in 5 categories and Qwen2.5-Max in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Qwen2.5-Max leads 41.4 to 33.7.
- The biggest single-benchmark swing is Confabulations: 13.2% for Claude Sonnet 4 and 21.8% for Qwen2.5-Max.
Side by side
| Claude Sonnet 4 | Qwen2.5-Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.8 | 40.7 |
| Released | 2025-05-22 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1414 | 1359 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Qwen2.5-Max: —
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Qwen2.5-Max leads
Claude Sonnet 4: 22.9 (#187), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1360 |
| Epoch Capabilities Index | 141.69 | 132.53 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 77.1% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |
| LiveBench | — | 62.3% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1375 | 1369 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| Confabulations | 13.2% | 21.8% |
| LMArena Expert | 1372 | 1337 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Qwen2.5-Max: —
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Qwen2.5-Max leads
Claude Sonnet 4: 46.7 (#156), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1333 | 1352 |
| LMArena Chinese | 1350 | 1382 |
| LMArena French | 1363 | 1396 |
| LMArena German | 1331 | 1350 |
| LMArena Japanese | 1302 | 1300 |
| LMArena Korean | 1291 | 1304 |
| LMArena Russian | 1355 | 1353 |
| LMArena Spanish | 1357 | 1377 |
Instruction Following Too close to call
Claude Sonnet 4: 71.7 (#145), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1376 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 84% | — |
Long Context Qwen2.5-Max leads
Claude Sonnet 4: 33.7 (#259), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1398 | 1358 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Claude Sonnet 4 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1351 | 1367 |
| LMArena Creative Writing | 1345 | 1339 |
| Short-Story Creative Writing | 81.4% | 72.9% |
| LMArena Multi-Turn | 1376 | 1364 |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Claude Sonnet 4 better than Qwen2.5-Max?
Claude Sonnet 4 and Qwen2.5-Max score almost the same on the Noometry Index (40.8 vs 40.7), so choose on price, context window or the category you care about most.
Is Claude Sonnet 4 or Qwen2.5-Max better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 41.8 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Qwen2.5-Max share?
20 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen2.5-Max has 27.