| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SemEval Task 1 2026 (test) | BT Rating1,323.7 | 13 | 5d ago | ||
| Electronic Sheep (test) | HOMER | Visual Understanding Avg Rank1.8 | 8 | 1mo ago | |
| Electronic sheep | HOMER | Mean Score3.31 | 7 | 1mo ago | |
| Humor in AI | HOMER | Mean Score3.54 | 7 | 1mo ago | |
| Humor Generation Human Evaluation Set | BART-DPO | WTR-H51 | 3 | 1mo ago |
