DeepSeek V4 Pro (0813) (Non-reasoning): benchmark results
Provider: DeepSeek. Released 2026-08-13. Access: Open.
Unified ELO 1532 ± 20, rank #804 of 2066 rated models, from 59 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 58 | Omniscience Index | 81 |
| AA-Omniscience Accuracy | 41.45 | Accuracy (%) | 80.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Go | 26 | Omniscience Index | 78.9 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 20 | Omniscience Index | 73.8 |
| AA-Omniscience Index - Software Engineering (SWE) - C | 38 | Omniscience Index | 73.7 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | -8 | Omniscience Index | 72.6 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 12.73 | Omniscience Index | 71.8 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 22 | Omniscience Index | 71.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Dart | -2 | Omniscience Index | 71.3 |
| AA-Omniscience Index - Software Engineering (SWE) | 6.6 | Omniscience Index | 71 |
| AA-Omniscience Index - Software Engineering (SWE) - R | -14 | Omniscience Index | 68.9 |
| AA-Omniscience Index - Health | -17.9 | Omniscience Index | 68.6 |
Interactive version: theaggregate.ai/model?slug=deepseek-v4-pro-0813-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-01.