Model comparison
Claude 3 Opus vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 29.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Qwen3 235B-A22B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 86.7% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 29.5 | 43.5 |
| Released | 2024-02-29 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 46 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Claude 3 Opus: 32.9 (#267), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| WeirdML | 19.2% | 41% |
| LMArena Coding | 1264 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Claude 3 Opus: 24.6 (#116), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Claude 3 Opus: 14.6 (#324), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 23.5% | 31% |
| Chess Puzzles | 5% | 12% |
| LMArena Hard Prompts | 1245 | 1433 |
| DTBench | 61.6% | 80.3% |
| LMCA | 17% | 29.3% |
| Epoch Capabilities Index | 126.91 | 143.85 |
| ForecastBench | 58.4 | 59.7 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Qwen3 235B-A22B leads
Claude 3 Opus: 14.8 (#299), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 86.7% |
| LMArena Math | 1273 | 1432 |
| MATH Level 5 | 37.5% | 68.9% |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Claude 3 Opus: 24.5 (#267), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 47.2% | 80.1% |
| SimpleQA Verified | 12.6% | 40.4% |
| Confabulations | 22.7% | 15.6% |
| LMArena Expert | 1223 | 1463 |
| MMLU-Pro | — | 84.4% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Qwen3 235B-A22B: —
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Qwen3 235B-A22B leads
Claude 3 Opus: 41.4 (#207), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1258 | 1409 |
| LMArena Chinese | 1248 | 1481 |
| LMArena French | 1275 | 1445 |
| LMArena German | 1258 | 1433 |
| LMArena Japanese | 1204 | 1399 |
| LMArena Korean | 1187 | 1391 |
| LMArena Russian | 1280 | 1411 |
| LMArena Spanish | 1246 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Claude 3 Opus: 64.1 (#228), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1248 | 1408 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Claude 3 Opus: 38.2 (#202), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1259 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Claude 3 Opus: 47.2 (#213), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Claude 3 Opus | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1262 | 1419 |
| LMArena Creative Writing | 1235 | 1384 |
| LMArena Multi-Turn | 1275 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Qwen3 235B-A22B share?
29 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen3 235B-A22B has 49.