Question Answering and Reasoning on Downstream Average 0-shot
60.5Average Accuracy
AIRAhybrid-D
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 60.5 | 62.2 | |
2026.05 | 60.3 | 61.5 | |
2026.05 | 60.3 | 62.1 | |
2026.05 | 60.2 | 61.9 | |
2026.05 | 60.2 | 61.6 | |
2026.05 | 60.1 | 61.8 | |
2026.05 | 59.9 | 61.6 | |
2026.05 | 59.9 | 61.2 | |
2026.05 | 59.8 | 61.7 | |
2026.05 | 59.6 | 60.9 | |
2026.05 | 59.2 | 60.1 | |
2026.05 | 59.2 | 61 |