DeepSeek·released 2025-08-21
Scored on 4 benchmarks. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Every score, ranked, colored by evidence status.
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| Lech Mazur Writing | 85.17accuracy (%) | unverified | 2025-08-21 |
| Fiction.LiveBench | 52.8accuracy (%) | unverified | 2025-08-21 |
| WeirdML | 38.36accuracy (%) | unverified | 2025-08-21 |
| SimpleBench | 28accuracy (%) | unverified | 2025-08-21 |