| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Airdialog (test) | lc-gpt-4-turbo | Runtime (s)3.23 | 2 | 4d ago | |
| IMDB (test) | lc-gpt-4-turbo | Runtime (s)4.37 | 2 | 4d ago | |
| ABCD (test) | UQE-claude-3-haiku | Runtime (s)3.34 | 2 | 4d ago | |
| Clevr (test) | UQE-claude-3-haiku | Runtime (seconds)3.13 | 2 | 4d ago |