Model comparison
Claude Sonnet 5 vs Qwen2-72B
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 30.2.
- The biggest single-benchmark swing is WeirdML: 68.8% for Claude Sonnet 5 and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | Qwen2-72B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 54.6 | 30.0 |
| Released | 2026-06-29 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Qwen2-72B: 29.1 (#310)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| WeirdML | 68.8% | 11.3% |
| LMArena Coding | 1483 | 1196 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), Qwen2-72B: 17.0 (#146)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| APEX-Agents | 54.5% | — |
| TheAgentCompany | — | 1.1% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| METR Time Horizons | — | 29.9% |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Qwen2-72B: 23.2 (#181)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1191 |
| Epoch Capabilities Index | 156.21 | 125.28 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Qwen2-72B: 30.2 (#236)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1467 | 1235 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Qwen2-72B: 21.2 (#275)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 90.5% | 40.8% |
| LMArena Expert | 1490 | 1171 |
| SimpleQA Verified | 33.7% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Qwen2-72B: —
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), Qwen2-72B: 35.9 (#244)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1431 | 1176 |
| LMArena Chinese | 1477 | 1240 |
| LMArena French | 1460 | 1170 |
| LMArena German | 1440 | 1151 |
| LMArena Japanese | 1422 | 1111 |
| LMArena Korean | 1411 | 1083 |
| LMArena Russian | 1451 | 1169 |
| LMArena Spanish | 1437 | 1169 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Qwen2-72B: 61.7 (#241)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1452 | 1181 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), Qwen2-72B: 36.1 (#235)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1463 | 1192 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Qwen2-72B: 40.8 (#241)
| Benchmark | Claude Sonnet 5 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1442 | 1203 |
| LMArena Creative Writing | 1416 | 1181 |
| LMArena Multi-Turn | 1454 | 1196 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Qwen2-72B?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.0 on the Noometry Index.
Is Claude Sonnet 5 or Qwen2-72B better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and Qwen2-72B share?
20 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Qwen2-72B has 26.