| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Osterhout and Mobley Semantic | Masked language model | Accuracy100 | 6 | 1mo ago | |
| Osterhout and Nicol Semantic | Masked language model | Accuracy100 | 6 | 1mo ago | |
| Warren Semantic | Masked language model | Accuracy1 | 6 | 1mo ago | |
| Pylkkänen and McElree Semantic | Masked language model | Accuracy95.5 | 6 | 1mo ago | |
| BLIMP Animacy | Masked language model | Accuracy78.7 | 6 | 1mo ago | |
| SAVANT | Qwen2.5-VL-7B (FT) | Accuracy94 | 4 | 9d ago | |
| CIFAR-10 Setting 2 | OCR-GAN | Plane Score99.9 | 2 | 1mo ago |
