| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SST2 (test) | PrivateLoRA | Accuracy96 | 233 | 3d ago | |
| SST-2 | RoBERTa Large | Accuracy95.99 | 184 | 25d ago | |
| MR | RoBERTa (Gao et al., 2021) | Accuracy90.8 | 148 | 1mo ago | |
| IMDB (test) | Our best (three tv-embeddings) | Error Rate0.0651 | 144 | 25d ago | |
| MR (test) | Accuracy90.8 | 142 | 1mo ago | ||
| CR | BYTE MLSTM | Accuracy91.4 | 142 | 1mo ago | |
| Stanford Sentiment Treebank SST-2 (test) | byte mLSTM | Accuracy91.8 | 99 | 1mo ago | |
| SST-2 64 instances (test) | Accuracy92.55 | 80 | 1mo ago | ||
| SST-2 | Attack Generation Rate99.67 | 58 | 3d ago | ||
| CR (test) | UniFew_meta | Mean Accuracy92.7 | 58 | 1mo ago | |
| SST-5 | LS | Accuracy70.67 | 46 | 16d ago | |
| Yelp (test) | ICL-gold | Accuracy96.4 | 46 | 1mo ago | |
| IMDB | SentriLlama 3.2 (3B) Instruct | Accuracy95.79 | 41 | 1mo ago | |
| Bangla (test) | GETR-GAT + HAL + TET | Macro F181 | 39 | 1mo ago | |
| SST (test) | 8k mLSTM | Accuracy93.8 | 37 | 1mo ago | |
| Yelp Polarity (test) | BERT-ITPT-FiT | Error Rate1.81 | 37 | 1mo ago | |
| Mpqa | PromptPATE | Accuracy92.1 | 35 | 1mo ago | |
| Marathi (test) | GETR-GAT + HAL | Macro F187 | 34 | 1mo ago | |
| Tweet (test) | ICL-gold | Accuracy48 | 34 | 1mo ago | |
| Yelp5 (test) | ICL-gold | Accuracy98.5 | 34 | 1mo ago | |
| Amz5 (test) | ICL-gold | Accuracy97 | 34 | 1mo ago | |
| Sentiment classification | LTV | Acc94.5 | 32 | 1mo ago | |
| Laptop14 | BOOSTAUG | Accuracy85.11 | 28 | 1mo ago | |
| Amz (test) | ICL-gold | Accuracy95.8 | 25 | 1mo ago | |
| SST-2 | UAT | Delta Accuracy0.05 | 24 | 1mo ago |
