Long-context Understanding on LongBench-Zh filtered (test)
64.8Single Document Score
Sentinel (Qwen2.5-0.5B-Instruct)
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| 64.8 | 25.1 | 14.3 | 34.7 | ||
| 63.3 | 24.9 | 14.8 | 34.3 | ||
2025.05 | 61.2 | 28.7 | 16 | 35.3 | |
2025.05 | 46.7 | 23 | 15.3 | 28.3 | |
2025.05 | 35.2 | 20.4 | 11.8 | 22.5 |