Long Context Evaluation on Long Context Benchmarks
32.3MDQA-10 Score
DD
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2024.05 | 32.3 | 26.9 | 24.6 | 30.7 | 34.2 | 30.9 | |
2024.05 | 29 | 23.8 | 20.5 | 26.2 | 32 | 27.5 | |
2024.05 | 26.7 | 20 | 22 | 28.7 | 34.6 | 28.7 | |
2024.05 | 25.6 | 19.8 | 16.9 | 29.2 | 33.1 | 27.7 | |
2024.05 | 24.4 | 20 | 16 | 29.2 | 32 | 27.1 |