PIT
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Paraphrase Identification | PIT -> PAWS (test) | AUROC77.5 | 20 | |
| Paraphrase Identification | PIT Out-of-distribution from PAWS | Macro F169.8 | 10 | |
| Paraphrase Identification | PIT -> PIT (test) | Macro F181 | 10 | |
| Locomotion | Pit Locomotion terrain | Success Rate (Rsucc)98.4 | 5 | |
| Image Semantic Embedding | PIT (internal evaluation) | Triplet Accuracy87.16 | 5 | |
| Paraphrase Identification | PIT | F1 Score0.755 | 2 |
Showing 6 of 6 rows