| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| E-KAR | Accuracy77.8 | 26 | 4d ago | ||
| UNIT 4 | ChatGPT | Accuracy92 | 22 | 4d ago | |
| SCAN (out-of-domain) | InstructGPT_003 + ANALOGYKB | Accuracy15.3 | 15 | 4d ago | |
| SAT (test) | ChatGPT + ANALOGYKB | Accuracy91 | 11 | 4d ago | |
| E-KAR (test) | InstructGPT003 + ANALOGYKB | Accuracy75 | 11 | 4d ago | |
| InstructGPT | Accuracy100 | 11 | 4d ago | ||
| UNIT 2 | ChatGPT | Accuracy94 | 11 | 4d ago | |
| BATS | ChatGPT | Accuracy96 | 11 | 4d ago | |
| SAT | ChatGPT | Accuracy0.91 | 11 | 4d ago |