Model comparison
Claude Opus 5 vs Qwen2.5-Max
Claude Opus 5 is the stronger model overall, scoring 67.7 to 40.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.1 to 24.6.
Side by side
| Claude Opus 5 | Qwen2.5-Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 67.7 | 40.1 |
| Released | 2026-07-24 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 57 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.0 (#5), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1533 | 1359 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1694 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| WeirdML | 91.8% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 2,165 | — |
Agentic & Tool Use Not comparable
Claude Opus 5: 55.5 (#1), Qwen2.5-Max: —
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.1 (#3), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1525 | 1360 |
| Epoch Capabilities Index | 162.67 | 132.54 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 29.1% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 59% | — |
| DTBench | 97.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |
| LiveBench | — | 62.3% |
Math Claude Opus 5 leads
Claude Opus 5: 86.1 (#6), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1533 | 1369 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 58.4% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#8), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1558 | 1337 |
| GPQA Diamond | 93.9% | — |
| SimpleQA Verified | 59.9% | — |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Claude Opus 5: 51.1 (#6), Qwen2.5-Max: —
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#3), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1500 | 1352 |
| LMArena Chinese | 1575 | 1382 |
| LMArena French | 1522 | 1396 |
| LMArena German | 1522 | 1350 |
| LMArena Japanese | 1510 | 1299 |
| LMArena Korean | 1526 | 1304 |
| LMArena Russian | 1507 | 1353 |
| LMArena Spanish | 1519 | 1377 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.3 (#5), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1516 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#20), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1516 | 1358 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.3 (#2), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Claude Opus 5 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1506 | 1367 |
| LMArena Creative Writing | 1491 | 1339 |
| LMArena Multi-Turn | 1496 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Claude Opus 5 better than Qwen2.5-Max?
Claude Opus 5 is the stronger model overall, scoring 67.7 to 40.1 on the Noometry Index.
Is Claude Opus 5 or Qwen2.5-Max better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 41.2 in the Noometry coding category.
How many benchmarks do Claude Opus 5 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Qwen2.5-Max has 27.