Model comparison
Claude 3.5 Sonnet vs Qwen2-72B
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 30.0 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 7 categories and Qwen2-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude 3.5 Sonnet leads 32.3 to 17.0.
- The biggest single-benchmark swing is WeirdML: 40% for Claude 3.5 Sonnet and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Qwen2-72B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 34.6 | 30.0 |
| Released | 2024-06-20 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Qwen2-72B: 29.1 (#310)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| WeirdML | 40% | 11.3% |
| BigCodeBench Instruct | 46.8% | 38.5% |
| LMArena Coding | 1342 | 1196 |
| BigCodeBench Complete | 58.6% | 54% |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| LiveBench Coding | 67.1% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Qwen2-72B: 17.0 (#146)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| TheAgentCompany | 24% | 1.1% |
| METR Time Horizons | 45.2% | 29.9% |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
Reasoning Too close to call
Claude 3.5 Sonnet: 23.1 (#183), Qwen2-72B: 23.2 (#181)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1191 |
| Epoch Capabilities Index | 133.55 | 125.28 |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Qwen2-72B leads
Claude 3.5 Sonnet: 19.2 (#288), Qwen2-72B: 30.2 (#236)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Math | 1307 | 1235 |
| MATH Level 5 | 56.9% | 39.1% |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 28.6 (#245), Qwen2-72B: 21.2 (#275)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 55.3% | 40.8% |
| LMArena Expert | 1265 | 1171 |
| MMLU | 87.3% | 82.4% |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Qwen2-72B: —
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 43.2 (#185), Qwen2-72B: 35.9 (#244)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1283 | 1176 |
| LMArena Chinese | 1272 | 1240 |
| LMArena French | 1305 | 1170 |
| LMArena German | 1297 | 1151 |
| LMArena Japanese | 1234 | 1111 |
| LMArena Korean | 1200 | 1083 |
| LMArena Russian | 1306 | 1169 |
| LMArena Spanish | 1290 | 1169 |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 68.8 (#182), Qwen2-72B: 61.7 (#241)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1181 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Qwen2-72B: 36.1 (#235)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1311 | 1192 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Qwen2-72B: 40.8 (#241)
| Benchmark | Claude 3.5 Sonnet | Qwen2-72B |
|---|---|---|
| LMArena Text | 1298 | 1203 |
| LMArena Creative Writing | 1292 | 1181 |
| LMArena Multi-Turn | 1326 | 1196 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Qwen2-72B?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 30.0 on the Noometry Index.
Is Claude 3.5 Sonnet or Qwen2-72B better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 29.1 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Qwen2-72B share?
26 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Qwen2-72B has 26.