Model comparison
Claude 3.5 Sonnet vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 34.4 on the Noometry Index.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 34.3 to 18.0.
- The biggest single-benchmark swing is LiveBench Data Analysis: 55% for Claude 3.5 Sonnet and 67.9% for Qwen2.5-Max.
Side by side
| Claude 3.5 Sonnet | Qwen2.5-Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 34.4 | 40.1 |
| Released | 2024-06-20 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Claude 3.5 Sonnet: 39.5 (#145), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 67.1% | 64.4% |
| LMArena Coding | 1343 | 1359 |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Qwen2.5-Max: —
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Qwen2.5-Max leads
Claude 3.5 Sonnet: 22.5 (#176), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 56.7% | 51.4% |
| LMArena Hard Prompts | 1305 | 1360 |
| LiveBench Data Analysis | 55% | 67.9% |
| Epoch Capabilities Index | 133.55 | 132.54 |
| LiveBench | 59% | 62.3% |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| DTBench | 67.8% | — |
| ForecastBench | 60.7 | — |
Math Qwen2.5-Max leads
Claude 3.5 Sonnet: 18.0 (#282), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 52.3% | 58.4% |
| LMArena Math | 1306 | 1369 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen2.5-Max leads
Claude 3.5 Sonnet: 28.5 (#236), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| Confabulations | 19.9% | 21.8% |
| LMArena Expert | 1264 | 1337 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), Qwen2.5-Max: —
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Qwen2.5-Max leads
Claude 3.5 Sonnet: 43.4 (#180), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1283 | 1352 |
| LMArena Chinese | 1271 | 1382 |
| LMArena French | 1304 | 1396 |
| LMArena German | 1297 | 1350 |
| LMArena Japanese | 1234 | 1299 |
| LMArena Korean | 1200 | 1304 |
| LMArena Russian | 1305 | 1353 |
| LMArena Spanish | 1289 | 1377 |
Instruction Following Qwen2.5-Max leads
Claude 3.5 Sonnet: 69.0 (#177), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 75.3% |
| LMArena Instruction Following | 1297 | 1335 |
| IFEval | 85.5% | — |
Long Context Qwen2.5-Max leads
Claude 3.5 Sonnet: 39.9 (#162), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1311 | 1358 |
Writing & Preference Qwen2.5-Max leads
Claude 3.5 Sonnet: 53.0 (#159), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Claude 3.5 Sonnet | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1298 | 1367 |
| LMArena Creative Writing | 1292 | 1339 |
| Short-Story Creative Writing | 80.3% | 72.9% |
| LMArena Multi-Turn | 1326 | 1364 |
| LiveBench Language | 53.8% | 56.3% |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Qwen2.5-Max share?
27 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Qwen2.5-Max has 27.