Model comparison
Claude Opus 4 vs Qwen3-30B-A3B
Claude Opus 4 is the stronger model overall, scoring 43.1 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 140× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. Claude Opus 4 scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.2 to 37.5.
- The biggest single-benchmark swing is Fiction.LiveBench: 61.1% for Claude Opus 4 and 40.6% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Opus 4 accepts more context: 200K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 43.1 | 38.9 |
| Released | 2025-05-22 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 200K | 41K |
| Max output | 32K | 16K |
| Input $ / M tokens | $15 | $0.12 |
| Output $ / M tokens | $75 | $0.50 |
| Results tracked | 56 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| WeirdML | 43.7% | 29.8% |
| LMArena Coding | 1442 | 1416 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| SciCode | — | 33.3% |
| GSO | 6.9% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 54.9% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1399 | 1398 |
| DTBench | 81.6% | 69.3% |
| LMCA | 37.4% | 22.4% |
| Epoch Capabilities Index | 142.67 | 139.63 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 35.7% | — |
| Chess Puzzles | — | 8% |
| EnigmaEval | 5.6% | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 70.3% |
| LMArena Math | 1390 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 76.3% | 70.1% |
| Confabulations | 15.9% | 12.3% |
| LMArena Expert | 1386 | 1396 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), Qwen3-30B-A3B: —
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Too close to call
Claude Opus 4: 48.8 (#138), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1362 | 1372 |
| LMArena Chinese | 1386 | 1433 |
| LMArena French | 1372 | 1418 |
| LMArena German | 1391 | 1380 |
| LMArena Japanese | 1331 | 1337 |
| LMArena Korean | 1321 | 1331 |
| LMArena Russian | 1392 | 1370 |
| LMArena Spanish | 1389 | 1404 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1363 |
| IFEval | 91.8% | — |
Long Context Claude Opus 4 leads
Claude Opus 4: 39.6 (#172), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | 61.1% | 40.6% |
| LMArena Longer Query | 1422 | 1379 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Claude Opus 4 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1377 | 1384 |
| LMArena Creative Writing | 1387 | 1317 |
| Short-Story Creative Writing | 83.6% | 75.3% |
| LMArena Multi-Turn | 1396 | 1378 |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Qwen3-30B-A3B?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 140× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Qwen3-30B-A3B better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 41K.
How many benchmarks do Claude Opus 4 and Qwen3-30B-A3B share?
28 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Qwen3-30B-A3B has 32.