Zero-shot Question Answering on (OpenBookQA, PIQA, RACE, SciQ, WinoGrande)
54.6Accuracy
Hyperloop
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 54.6 | |
2026.04 | 53.7 | |
2026.04 | 53.3 | |
2026.04 | 52.8 | |
2026.04 | 49.8 | |
2026.04 | 49.2 | |
2026.04 | 48.6 | |
2026.04 | 48 | |
2026.04 | 41.6 | |
2026.04 | 41.4 | |
2026.04 | 41.1 | |
2026.04 | 41.1 |