Model comparison
Claude 3 Sonnet vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 29.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Qwen Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen Max leads 22.3 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 67.2% for Qwen Max.
Side by side
| Claude 3 Sonnet | Qwen Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 29.0 | 34.7 |
| Released | 2024-02-29 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 30 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Claude 3 Sonnet: 29.6 (#302), Qwen Max: 30.7 (#292)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Coding | 1223 | 1288 |
| Aider Polyglot | — | 21.8% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Qwen Max leads
Claude 3 Sonnet: 20.5 (#237), Qwen Max: 25.1 (#151)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1269 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Qwen Max leads
Claude 3 Sonnet: 10.7 (#310), Qwen Max: 22.3 (#276)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 16.1% |
| LMArena Math | 1213 | 1275 |
| MATH Level 5 | 18.2% | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
Claude 3 Sonnet: 21.1 (#276), Qwen Max: 30.3 (#228)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| GPQA Diamond | 40.6% | 56.1% |
| LMArena Expert | 1173 | 1248 |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Qwen Max: —
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Qwen Max leads
Claude 3 Sonnet: 37.8 (#234), Qwen Max: 41.8 (#202)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Non-English | 1205 | 1263 |
| LMArena Chinese | 1189 | 1254 |
| LMArena French | 1229 | 1330 |
| LMArena German | 1204 | 1254 |
| LMArena Japanese | 1131 | 1205 |
| LMArena Korean | 1128 | 1142 |
| LMArena Russian | 1227 | 1274 |
| LMArena Spanish | 1204 | 1290 |
Instruction Following Qwen Max leads
Claude 3 Sonnet: 62.8 (#235), Qwen Max: 66.5 (#208)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1199 | 1262 |
Long Context Qwen Max leads
Claude 3 Sonnet: 36.7 (#228), Qwen Max: 39.4 (#180)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1211 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Claude 3 Sonnet: 42.1 (#238), Qwen Max: 47.8 (#205)
| Benchmark | Claude 3 Sonnet | Qwen Max |
|---|---|---|
| LMArena Text | 1218 | 1282 |
| LMArena Creative Writing | 1186 | 1248 |
| LMArena Multi-Turn | 1227 | 1277 |
Frequently asked questions
Is Claude 3 Sonnet better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Qwen Max share?
20 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen Max has 23.