Model comparison
Claude Sonnet 4 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 40.6 on the Noometry Index.
Last verified . 44 shared benchmarks.
Alibaba (Qwen)Summary
- They share 44 benchmarks with published results for both. Claude Sonnet 4 scores higher in 3 categories and Qwen3 235B-A22B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Qwen3 235B-A22B leads 46.1 to 33.6.
- The biggest single-benchmark swing is ARC-AGI-1: 40% for Claude Sonnet 4 and 11% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.6 | 43.2 |
| Released | 2025-05-22 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 16K |
| Input $ / M tokens | $3 | $0.70 |
| Output $ / M tokens | $15 | $2.80 |
| Results tracked | 58 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Sonnet 4: 44.0 (#70), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 61.3% | 59.6% |
| SciCode | 40% | 42.4% |
| WeirdML | 46.1% | 41% |
| LMArena Coding | 1414 | 1445 |
| SWE-bench Verified (bash only) | 64.9% | — |
| GSO | 4.9% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.3 (#29), Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 23.0 (#169), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 5.9% | 1.3% |
| SimpleBench | 45.5% | 31% |
| Kagi LLM Benchmark | 73% | 69.4% |
| ARC-AGI-1 | 40% | 11% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1372 | 1433 |
| DTBench | 77.1% | 80.3% |
| LMCA | 29% | 29.3% |
| Epoch Capabilities Index | 141.69 | 143.87 |
| ForecastBench | 60.2 | 59.7 |
| Chess Puzzles | — | 12% |
| EnigmaEval | 3.1% | — |
| Mystery Game Puzzles | — | 9% |
Math Qwen3 235B-A22B leads
Claude Sonnet 4: 41.5 (#71), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 86.7% |
| Omni-MATH | 60.2% | 71.8% |
| LMArena Math | 1375 | 1431 |
| MATH Level 5 | 84.4% | 68.9% |
| FrontierMath (Feb 2025 set) | 4.1% | 8.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
Knowledge Qwen3 235B-A22B leads
Claude Sonnet 4: 41.6 (#99), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 79.2% | 80.1% |
| MMLU-Pro | 84.3% | 84.4% |
| Confabulations | 13.2% | 15.6% |
| Vectara Hallucination Rate | 10.3% | 9.3% |
| GPQA (HELM) | 70.6% | 72.7% |
| LMArena Expert | 1371 | 1460 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 40.4% |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), Qwen3 235B-A22B: —
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Qwen3 235B-A22B leads
Claude Sonnet 4: 46.9 (#151), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1333 | 1410 |
| LMArena Chinese | 1351 | 1481 |
| LMArena French | 1364 | 1445 |
| LMArena German | 1331 | 1432 |
| LMArena Japanese | 1301 | 1400 |
| LMArena Korean | 1293 | 1391 |
| LMArena Russian | 1355 | 1411 |
| LMArena Spanish | 1356 | 1429 |
Instruction Following Too close to call
Claude Sonnet 4: 71.8 (#141), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 84% | 83.5% |
| LMArena Instruction Following | 1375 | 1408 |
Long Context Qwen3 235B-A22B leads
Claude Sonnet 4: 33.6 (#254), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | 46.9% | 75% |
| LMArena Longer Query | 1398 | 1426 |
Writing & Preference Qwen3 235B-A22B leads
Claude Sonnet 4: 57.3 (#127), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Claude Sonnet 4 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1351 | 1419 |
| LMArena Creative Writing | 1345 | 1384 |
| Short-Story Creative Writing | 81.4% | 83% |
| EQ-Bench Creative Writing | 1483 | 1366 |
| WildBench | 83.8% | 86.6% |
| LMArena Multi-Turn | 1376 | 1432 |
Frequently asked questions
Is Claude Sonnet 4 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Qwen3 235B-A22B better for coding?
They score almost the same on coding (44.0 vs 43.8); test both on your own repository before choosing.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 131K.
How many benchmarks do Claude Sonnet 4 and Qwen3 235B-A22B share?
44 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen3 235B-A22B has 49.