Model comparison
Claude 3.7 Sonnet vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Qwen3.8 27B in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 87.5% for Qwen3.8 27B.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Qwen3.8 27B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 46.0 |
| Released | 2025-02-24 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 58 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Claude 3.7 Sonnet: 40.6 (#136), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1361 | 1482 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Qwen3.8 27B: 32.9 (#57)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Qwen3.8 27B leads
Claude 3.7 Sonnet: 18.6 (#277), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| ARC-AGI-2 | 0.9% | 42.4% |
| ARC-AGI-1 | 28.6% | 87.5% |
| LMArena Hard Prompts | 1333 | 1460 |
| Epoch Capabilities Index | 141.16 | 149.38 |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 88% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Too close to call
Claude 3.7 Sonnet: 37.5 (#153), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1337 | 1456 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 16% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Qwen3.8 27B leads
Claude 3.7 Sonnet: 39.8 (#130), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1321 | 1482 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Qwen3.8 27B leads
Claude 3.7 Sonnet: 33.7 (#95), Qwen3.8 27B: 41.3 (#37)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1169 | 1271 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Qwen3.8 27B leads
Claude 3.7 Sonnet: 44.1 (#179), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1296 | 1430 |
| LMArena Chinese | 1299 | 1504 |
| LMArena French | 1303 | 1465 |
| LMArena German | 1301 | 1438 |
| LMArena Japanese | 1267 | 1384 |
| LMArena Korean | 1249 | 1393 |
| LMArena Russian | 1311 | 1415 |
| LMArena Spanish | 1298 | 1448 |
Instruction Following Qwen3.8 27B leads
Claude 3.7 Sonnet: 72.9 (#125), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1439 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1373 | 1450 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Qwen3.8 27B leads
Claude 3.7 Sonnet: 54.4 (#150), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Claude 3.7 Sonnet | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1314 | 1441 |
| LMArena Creative Writing | 1332 | 1384 |
| EQ-Bench Creative Writing | 1412 | 1671 |
| LMArena Multi-Turn | 1339 | 1441 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Qwen3.8 27B share?
22 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3.8 27B has 31.