Model comparison
Claude 3.5 Sonnet vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.6 on the Noometry Index.
Last verified . 36 shared benchmarks.
Alibaba (Qwen)Summary
- They share 36 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 86.7% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 34.6 | 43.5 |
| Released | 2024-06-20 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 60 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 39.0 (#165), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 51.6% | 59.6% |
| WeirdML | 40% | 41% |
| LMArena Coding | 1342 | 1445 |
| SciCode | — | 42.4% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 32.3 (#67), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 41.4% | 31% |
| LMArena Hard Prompts | 1305 | 1433 |
| DTBench | 67.8% | 80.3% |
| Epoch Capabilities Index | 133.55 | 143.85 |
| ForecastBench | 60.7 | 59.7 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 29.3% |
| LiveBench | 59% | — |
Math Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 19.2 (#288), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 86.7% |
| Omni-MATH | 27.6% | 71.8% |
| LMArena Math | 1307 | 1432 |
| MATH Level 5 | 56.9% | 68.9% |
| FrontierMath (Feb 2025 set) | 2.1% | 8.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| LiveBench Math | 52.3% | — |
Knowledge Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 28.6 (#245), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 55.3% | 80.1% |
| MMLU-Pro | 77.7% | 84.4% |
| Confabulations | 19.9% | 15.6% |
| GPQA (HELM) | 56.5% | 72.7% |
| LMArena Expert | 1265 | 1463 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 40.4% |
| Vectara Hallucination Rate | — | 9.3% |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Qwen3 235B-A22B: —
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 43.2 (#185), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1283 | 1409 |
| LMArena Chinese | 1272 | 1481 |
| LMArena French | 1305 | 1445 |
| LMArena German | 1297 | 1433 |
| LMArena Japanese | 1234 | 1399 |
| LMArena Korean | 1200 | 1391 |
| LMArena Russian | 1306 | 1411 |
| LMArena Spanish | 1290 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 68.8 (#182), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 85.5% | 83.5% |
| LMArena Instruction Following | 1297 | 1408 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 39.9 (#167), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1311 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Claude 3.5 Sonnet: 52.9 (#164), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Claude 3.5 Sonnet | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1298 | 1419 |
| LMArena Creative Writing | 1292 | 1384 |
| Short-Story Creative Writing | 80.3% | 83% |
| EQ-Bench Creative Writing | 1451 | 1366 |
| WildBench | 79.2% | 86.6% |
| LMArena Multi-Turn | 1326 | 1432 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Qwen3 235B-A22B share?
36 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Qwen3 235B-A22B has 49.