Model comparison
Claude 3.5 Sonnet vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 34.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Qwen3.5 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 27B leads 38.8 to 19.2.
- The biggest single-benchmark swing is DTBench: 67.8% for Claude 3.5 Sonnet and 82.4% for Qwen3.5 27B.
- Qwen3.5 27B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Qwen3.5 27B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 34.6 | 41.9 |
| Released | 2024-06-20 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 60 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Sonnet: 39.0 (#165), Qwen3.5 27B: 38.9 (#168)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| WeirdML | 40% | 39.5% |
| LMArena Coding | 1342 | 1427 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1358 |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 349.45 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Qwen3.5 27B: —
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Claude 3.5 Sonnet: 23.1 (#183), Qwen3.5 27B: 27.5 (#117)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1414 |
| DTBench | 67.8% | 82.4% |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 47.9% |
| EnigmaEval | 0.9% | — |
| Thematic Generalization | — | 45.5% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 34% |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Qwen3.5 27B leads
Claude 3.5 Sonnet: 19.2 (#288), Qwen3.5 27B: 38.8 (#127)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1307 | 1429 |
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.5 27B leads
Claude 3.5 Sonnet: 28.6 (#245), Qwen3.5 27B: 38.0 (#150)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1265 | 1428 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 12.1% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Qwen3.5 27B leads
Claude 3.5 Sonnet: 26.5 (#120), Qwen3.5 27B: 39.4 (#59)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | 1125 | 1241 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Qwen3.5 27B leads
Claude 3.5 Sonnet: 43.2 (#185), Qwen3.5 27B: 50.8 (#115)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1283 | 1390 |
| LMArena Chinese | 1272 | 1478 |
| LMArena French | 1305 | 1410 |
| LMArena German | 1297 | 1393 |
| LMArena Japanese | 1234 | 1345 |
| LMArena Korean | 1200 | 1358 |
| LMArena Russian | 1306 | 1390 |
| LMArena Spanish | 1290 | 1407 |
Instruction Following Qwen3.5 27B leads
Claude 3.5 Sonnet: 68.8 (#182), Qwen3.5 27B: 73.5 (#119)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1393 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Qwen3.5 27B leads
Claude 3.5 Sonnet: 39.9 (#167), Qwen3.5 27B: 43.1 (#106)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1311 | 1413 |
Writing & Preference Qwen3.5 27B leads
Claude 3.5 Sonnet: 52.9 (#164), Qwen3.5 27B: 59.3 (#111)
| Benchmark | Claude 3.5 Sonnet | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1298 | 1409 |
| LMArena Creative Writing | 1292 | 1362 |
| LMArena Multi-Turn | 1326 | 1410 |
| 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 Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Qwen3.5 27B better for coding?
They score almost the same on coding (39.0 vs 38.9); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Sonnet and Qwen3.5 27B share?
20 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Qwen3.5 27B has 28.