Claude Sonnet 5 vs Deepseek v4 Pro
Claude Sonnet 5 
Deepseek v4 Pro Verdict
- Claude Sonnet 5 (high) and Deepseek v4 Pro (high) are level on quality (60.0 vs 60.4).
- Claude Sonnet 5 (high) is stronger in agents & tools, coding, composite, knowledge, long context, multimodal, reasoning.
- Deepseek v4 Pro (high) is stronger in human preference, maths.
| Metric | Claude Sonnet 5 (high) | Deepseek v4 Pro (high) |
|---|---|---|
| BenchLeader Index | 60.0 | 60.4 |
| Agents & tools score | 60.8 | – |
| Coding score | 61.5 | 59.3 |
| Composite score | 63.4 | – |
| Human preference score | 65.9 | 66.0 |
| Knowledge score | 58.9 | – |
| Long context score | 62.1 | – |
| Multimodal score | 63.1 | – |
| Reasoning score | 66.5 | 65.9 |
| Maths score | – | 66.2 |
| Blended price $/M | $4.00 | – |
| Output speed | 68 tok/s | – |
| Time to first answer | 1.8 s | – |
| Context window | 1M | – |
| GPQA Diamond | – | 90.9% |
| OTIS Mock AIME | – | 95.6% |
| SciCode | 48.6% | 46.4% |
| WeirdML | 68.8% | 46.5% |
| LMArena Text | 1461 | 1462 |
| LMArena Hard Prompts | 1488 | 1482 |
| LMArena Coding | 1521 | 1505 |
| LMArena WebDev | 1537 | 1581 |
| LMArena Vision | 1278 | – |
| LMArena Agent | 5.9 | – |
| AA Intelligence Index | 32.0 | – |
| AA-LCR | 76.7% | – |
| AA-Omniscience | -3.7 | – |
| Humanity's Last Exam (AA) | 35.7% | – |
| SciCode (AA) | 54.3% | – |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5 vs Deepseek v4 Pro: questions
- Is Claude Sonnet 5 better than Deepseek v4 Pro?
- Claude Sonnet 5 (high) and Deepseek v4 Pro (high) are level on quality (60.0 vs 60.4). The BenchLeader Index combines every independent quality benchmark; Deepseek v4 Pro (high) is ahead overall as of 2026-09-13, but check the category scores for your use.
- Is Claude Sonnet 5 better than Deepseek v4 Pro for coding?
- Claude Sonnet 5 scores higher in coding (62 vs 59 on the category index, where 50 is average).