deepseek-v4-pro-high-preview: benchmark results
Provider: DeepSeek.
Aggregate Rating 1746 ± 41, rank #197 of 10916 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chatbot Arena (Text - Medicine & Healthcare) | 1485 | Arena Score | 88.9 |
| Chatbot Arena (Text - Korean) | 1435 | Arena Score | 87.9 |
| Chatbot Arena (Text - Legal & Government) | 1473 | Arena Score | 86.8 |
| Chatbot Arena (Text - Creative Writing) | 1440 | Arena Score | 86.3 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1480 | Arena Score | 86.1 |
| Chatbot Arena (Text - Math) | 1466 | Arena Score | 85.7 |
| Chatbot Arena (Text - Chinese) | 1500 | Arena Score | 85.1 |
| Chatbot Arena (Text - English) | 1467 | Arena Score | 84.4 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1432 | Arena Score | 84.1 |
| Chatbot Arena (Text - Mathematical) | 1468 | Arena Score | 84.1 |
| Chatbot Arena (Text - Instruction Following) | 1448 | Arena Score | 83.8 |
| Chatbot Arena (Text - Hard Prompts (English)) | 1483 | Arena Score | 83.7 |
Interactive version: theaggregate.ai/model?slug=deepseek-v4-pro-high-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.