| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Big Five generation | Memory Inception | GAS Score0.44 | 6 | 26d ago | |
| Big Five self-eval | Memory Inception | DAS0.775 | 6 | 26d ago | |
| SPBench | SFT | Agreeableness (A) Mean Score9.67 | 6 | 1mo ago | |
| Myopic Reward (test) | CAA | Myopic Score74 | 5 | 3mo ago | |
| SPBench & PersonalityBench (Human Evaluation) | IRIS | 1st Rank Distribution (%)35.4 | 4 | 1mo ago |
