deepseek-v4-flash-high-preview: benchmark results
Provider: DeepSeek.
Aggregate Rating 1715 ± 40, rank #284 of 10916 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chatbot Arena (Text - Legal & Government) | 1458 | Arena Score | 79.3 |
| Chatbot Arena (Text - Instruction Following) | 1434 | Arena Score | 78.5 |
| Chatbot Arena (Text - Creative Writing) | 1410 | Arena Score | 78.2 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1422 | Arena Score | 78.2 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1460 | Arena Score | 78.1 |
| Chatbot Arena (Text - English) | 1450 | Arena Score | 77.8 |
| Chatbot Arena (Text - Japanese) | 1426 | Arena Score | 77.8 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1408 | Arena Score | 77.5 |
| Chatbot Arena (Text - Chinese) | 1480 | Arena Score | 77.4 |
| Chatbot Arena (Text - Math) | 1441 | Arena Score | 77.3 |
| Chatbot Arena (Text - Medicine & Healthcare) | 1461 | Arena Score | 77 |
| Chatbot Arena (Text - Longer Query) | 1449 | Arena Score | 76.7 |
Interactive version: theaggregate.ai/model?slug=deepseek-v4-flash-high-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.