Question Answering on OpenBook QA (test)
28.8Accuracy
MDLM
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.05 | 28.8 | |
2025.05 | 28.6 | |
2026.02 | 28.6 | |
2026.02 | 27.8 | |
2025.05 | 26.6 | |
2025.05 | 25.8 | |
2025.05 | 25.4 | |
2026.02 | 25.4 | |
2025.05 | 25 | |
2026.02 | 23.4 | |
2026.02 | 23 | |
2026.02 | 19 |