Model comparison
Claude Opus 4 vs Qwen3 Max
Claude Opus 4 and Qwen3 Max score almost the same on the Noometry Index (43.1 vs 43.7), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Claude Opus 4 scores higher in 4 categories and Qwen3 Max in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3 Max leads 53.7 to 48.8.
- The biggest single-benchmark swing is MATH Level 5: 85% for Claude Opus 4 and 97.1% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Qwen3 Max accepts more context: 262K tokens versus 200K.
Side by side
| Claude Opus 4 | Qwen3 Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 43.1 | 43.7 |
| Released | 2025-05-22 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 262K |
| Max output | 32K | 66K |
| Input $ / M tokens | $15 | $1.20 |
| Output $ / M tokens | $75 | $6 |
| Results tracked | 56 | 33 |
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 Max: 43.0 (#93)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1442 | 1456 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | — | 370.45 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Not comparable
Claude Opus 4: 34.8 (#42), Qwen3 Max: —
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Qwen3 Max: 22.6 (#190)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 72.5% |
| LMArena Hard Prompts | 1399 | 1448 |
| DTBench | 81.6% | 82.1% |
| LMCA | 37.4% | 28.3% |
| Epoch Capabilities Index | 142.67 | 142.38 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 5.6% | — |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Qwen3 Max: 38.7 (#131)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 73.3% |
| LMArena Math | 1390 | 1446 |
| MATH Level 5 | 85% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 61.6% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3 Max leads
Claude Opus 4: 44.0 (#88), Qwen3 Max: 48.1 (#78)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 76.3% | 72.6% |
| LMArena Expert | 1386 | 1455 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), Qwen3 Max: —
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Qwen3 Max leads
Claude Opus 4: 48.8 (#138), Qwen3 Max: 53.7 (#62)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1362 | 1429 |
| LMArena Chinese | 1386 | 1478 |
| LMArena French | 1372 | 1449 |
| LMArena German | 1391 | 1463 |
| LMArena Japanese | 1331 | 1397 |
| LMArena Korean | 1321 | 1399 |
| LMArena Russian | 1392 | 1428 |
| LMArena Spanish | 1389 | 1462 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Qwen3 Max: 74.8 (#87)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1406 | 1419 |
| IFEval | 91.8% | — |
Long Context Qwen3 Max leads
Claude Opus 4: 39.6 (#172), Qwen3 Max: 41.6 (#134)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 61.1% | 66.7% |
| LMArena Longer Query | 1422 | 1438 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Claude Opus 4: 61.2 (#89), Qwen3 Max: 62.4 (#76)
| Benchmark | Claude Opus 4 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1377 | 1439 |
| LMArena Creative Writing | 1387 | 1402 |
| LMArena Multi-Turn | 1396 | 1446 |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Qwen3 Max?
Claude Opus 4 and Qwen3 Max score almost the same on the Noometry Index (43.1 vs 43.7), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Opus 4 or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Qwen3 Max better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4 and Qwen3 Max share?
25 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Qwen3 Max has 33.