Generative sense-making QA on LongBench
0.6573Comprehensiveness
HGMEM
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 0.6573 | 0.6974 | |
2025.12 | 0.6418 | 0.6651 | |
2025.12 | 0.6362 | 0.6598 | |
2025.12 | 0.6218 | 0.6582 | |
2025.12 | 0.6162 | 0.642 | |
2025.12 | 0.6155 | 0.6337 | |
2025.12 | 0.6145 | 0.6356 | |
2025.12 | 0.6141 | 0.6225 | |
2025.12 | 0.6082 | 0.6273 | |
2025.12 | 0.6078 | 0.6216 | |
2025.12 | 0.6074 | 0.6128 | |
2025.12 | 0.6039 | 0.6402 | |
2025.12 | 0.5892 | 0.6127 | |
2025.12 | 0.5666 | 0.608 |