Deepseek v4 Pro vs GPT-5 Pro
Deepseek v4 Pro 
GPT-5 Pro Verdict
- Deepseek v4 Pro (high) and GPT-5 Pro are level on quality (60.4 vs 60.8).
- Deepseek v4 Pro (high) is stronger in coding, human preference, maths, reasoning.
- GPT-5 Pro is stronger in knowledge, multimodal.
| Metric | Deepseek v4 Pro (high) | GPT-5 Pro |
|---|---|---|
| BenchLeader Index | 60.4 | 60.8 |
| Coding score | 59.3 | – |
| Human preference score | 66.0 | – |
| Maths score | 66.2 | – |
| Reasoning score | 65.9 | 57.6 |
| Knowledge score | – | 68.0 |
| Multimodal score | – | 67.4 |
| Blended price $/M | – | $41.25 |
| Context window | – | 400k |
| GPQA Diamond | 90.9% | – |
| OTIS Mock AIME | 95.6% | – |
| Humanity's Last Exam | – | 31.6% |
| SimpleBench | – | 61.6% |
| SciCode | 46.4% | – |
| WeirdML | 46.5% | – |
| Epoch Capabilities Index | – | 150.3 |
| LMArena Text | 1462 | – |
| LMArena Hard Prompts | 1482 | – |
| LMArena Coding | 1505 | – |
| LMArena WebDev | 1581 | – |
| PRBench Finance | – | 51.1% |
| PRBench Legal | – | 49.9% |
| VISTA | – | 52.4% |
| MultiNRC | – | 65.2% |
| Kagi LLM Benchmark | – | 76.8% |
| ARC-AGI-1 | – | 70.2% |
| ARC-AGI-2 | – | 18.3% |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Deepseek v4 Pro vs GPT-5 Pro: questions
- Is Deepseek v4 Pro better than GPT-5 Pro?
- Deepseek v4 Pro (high) and GPT-5 Pro are level on quality (60.4 vs 60.8). The BenchLeader Index combines every independent quality benchmark; GPT-5 Pro is ahead overall as of 2026-09-13, but check the category scores for your use.