| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| IMDB (test) | Accuracy97.42 | 248 | 3d ago | ||
| SST-5 (test) | CAPO | Accuracy62.27 | 173 | 3d ago | |
| SST-2 | UD+-XXL | Accuracy97.48 | 156 | 3d ago | |
| MR | ICL | Accuracy0.939 | 142 | 3d ago | |
| SST-2 (test) | Accuracy97.1 | 136 | 2d ago | ||
| CR | FADS-ICL | Accuracy96.4 | 123 | 3d ago | |
| IMDB | UD+-XXL | Accuracy97.44 | 57 | 3d ago | |
| CR | RoRA | CA93.81 | 54 | 3d ago | |
| SST-2 (test) | Clean Accuracy96.43 | 50 | 3d ago | ||
| SST-5 | MUPPET | Accuracy94.84 | 47 | 2d ago | |
| SST-2 GLUE | KEN | F1 Score94.9 | 45 | 3d ago | |
| AR | RLLR | Accuracy70.9 | 45 | 3d ago | |
| SST-2 (dev) | UNIMO | Accuracy96.8 | 41 | 3d ago | |
| CMU-MOSEI (test) | MISA | Acc (2-class)85.5 | 40 | 3d ago | |
| Yelp P. (test) | SWEM-hier | Accuracy95.81 | 40 | 3d ago | |
| Financial Phrasebank | ColD-Fusion | Accuracy86.72 | 37 | 3d ago | |
| IMDB (test) | RanMASK | Clean Accuracy (%)94.33 | 37 | 3d ago | |
| FPB | Latent Concept Learning | Accuracy64.5 | 35 | 3d ago | |
| SST-2 | Merge | Accuracy96.71 | 33 | 3d ago | |
| ChnSentiCorp (test) | MacBERT | Accuracy95.9 | 33 | 3d ago | |
| ChnSentiCorp (dev) | ERNIE 2.0 | Accuracy96.1 | 33 | 3d ago | |
| Yelp '13 (test) | HUAPA | Accuracy68.3 | 33 | 3d ago | |
| SST-2 | RLLR | Accuracy96.9 | 31 | 3d ago | |
| SST-2 | BadNet | ACC96 | 30 | 3d ago | |
| Yelp | DecT | Accuracy95.6 | 30 | 3d ago |
