Short-answer Question Answering on HotPotQA (EM, F1)
40.8EM
APCD
Updated 22d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 40.8 | 39.2 | |
2026.05 | 39.6 | 36.8 | |
2026.05 | 39.2 | 37 | |
2026.05 | 38.8 | 36.8 | |
2026.05 | 37.8 | 32.6 | |
2026.05 | 35.2 | 33.3 | |
2026.05 | 33.6 | 28.8 | |
2026.05 | 33.4 | 28.8 | |
2026.05 | 33.3 | 28.6 | |
2026.05 | 33.1 | 28.3 | |
2026.05 | 30.1 | 26.5 | |
2026.05 | 28.4 | 29.4 | |
2026.05 | 27.4 | 25.4 | |
2026.05 | 26.6 | 23.7 | |
2026.05 | 26.3 | 24.3 | |
2026.05 | 26.1 | 24.2 | |
2026.05 | 25.8 | 22.6 | |
2026.05 | 25.5 | 23.4 | |
2026.05 | 24.8 | 24.4 | |
2026.05 | 24.3 | 18.8 | |
2026.05 | 21.7 | 20.6 |