Claude Opus 5.5 vs Deepseek v4 Pro High
Claude Opus 5.5 
Deepseek v4 Pro High Verdict
- Claude Opus 5.5 (thinking) leads on quality: 70.7 vs 60.8.
- Claude Opus 5.5 (thinking) is stronger in composite, knowledge, long context, multimodal, reasoning.
- Deepseek v4 Pro High (high) is stronger in coding, human preference, maths.
| Metric | Claude Opus 5.5 (thinking) | Deepseek v4 Pro High (high) |
|---|---|---|
| BenchLeader Index | 70.7 | 60.8 |
| Composite score | 95.0 | – |
| Knowledge score | 85.0 | – |
| Long context score | 68.5 | – |
| Multimodal score | 71.9 | – |
| Reasoning score | 95.0 | 66.0 |
| Coding score | – | 59.0 |
| Human preference score | – | 66.2 |
| Maths score | – | 66.2 |
| Blended price $/M | $8.00 | – |
| Output speed | 48 tok/s | – |
| Time to first answer | 4.2 s | – |
| Context window | 1M | – |
| GPQA Diamond | – | 90.9% |
| OTIS Mock AIME | – | 95.6% |
| SciCode | – | 46.4% |
| WeirdML | – | 46.5% |
| LMArena Text | – | 1463 |
| LMArena Hard Prompts | – | 1482 |
| LMArena Coding | – | 1503 |
| LMArena WebDev | – | 1581 |
| AA Intelligence Index | 57.6 | – |
| AA-LCR | 84.7% | – |
| MMMU-Pro | 87.7% | – |
| AA-Omniscience | 46.4 | – |
| Humanity's Last Exam (AA) | 61.4% | – |
| SciCode (AA) | 66.9% | – |
| CritPt | 31.7% | – |
| GDPval (AA) | 67.3% | – |
| LMArena Maths | – | 1469 |
| LMArena Creative Writing | – | 1442 |
| LMArena Instruction Following | – | 1457 |
| LMArena Multi-turn | – | 1469 |
| LMArena Longer Queries | – | 1474 |
| Chess Puzzles | – | 13.0% |
| CL-bench Life | – | 13.5% |
| Surface Evolver Bench | – | 40.0% |
| ALE-Bench | – | 1006.1 |
| Terminal-Bench 4.0 (AA) | 59.6% | – |
| AutomationBench | 69.5% | – |
| GDP.pdf | 26.2% | – |
| Harvey LAB | 91.2% | – |
| AA-Omniscience: accuracy | 66.2% | – |
| AA-Omniscience: non-hallucination | 41.4% | – |
| AA-Briefcase | 1822 | – |
Data as of 2026-09-22. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 5.5 vs Deepseek v4 Pro High: questions
- Is Claude Opus 5.5 better than Deepseek v4 Pro High?
- Claude Opus 5.5 (thinking) leads on quality: 70.7 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5.5 (thinking) is ahead overall as of 2026-09-22, but check the category scores for your use.