| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| T2I-FactualBench-SKCM 100 pairs (test) | FAGER | Pairwise Accuracy87 | 3 | 2mo ago | |
| Culture 30 pairs (test) | FAGER | Pairwise Accuracy97 | 3 | 2mo ago | |
| ABO 50 pairs (test) | FAGER | Pairwise Accuracy82 | 3 | 2mo ago | |
| I-HallA History 99 pairs (test) | FAGER | Pairwise Accuracy83 | 3 | 2mo ago | |
| I-HallA-Science 99 pairs (test) | FAGER | Pairwise Accuracy73 | 3 | 2mo ago |