Long-context Question Answering on 2WikiMQA
79.5SubEM
LongMab
Updated 8d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.08 | 79.5 | 68.83 | |
2025.08 | 78 | 67.85 | |
2025.08 | 77.5 | 74.32 | |
2025.08 | 77.5 | 66.52 | |
2025.08 | 77 | 72.4 | |
2025.08 | 77 | 73.38 | |
2025.08 | 76 | 70.08 | |
2025.08 | 76 | 68.6 | |
2025.08 | 75.5 | 73.16 | |
2025.08 | 75.5 | 71.34 | |
2025.08 | 75.5 | 63.88 | |
2025.08 | 75.5 | 72.8 | |
2025.08 | 75 | 57.91 | |
2025.08 | 73.5 | 62.3 | |
2025.08 | 73 | 64.01 | |
2025.08 | 71 | 68.76 | |
2025.08 | 70 | 61.55 | |
2025.08 | 69.5 | 65.45 | |
2025.08 | 69.5 | 63.64 | |
2025.08 | 69 | 59.35 | |
2025.08 | 69 | 65.45 | |
2025.08 | 68.5 | 65.26 | |
2025.08 | 68.5 | 63.23 | |
2025.08 | 68 | 67.07 | |
2025.08 | 67.5 | 62.97 | |
2025.08 | 67 | 36.39 | |
2025.08 | 66 | 66.79 | |
2025.08 | 66 | 53.93 | |
2025.08 | 63 | 61.74 | |
2025.08 | 63 | 57.2 | |
2025.08 | 62 | 54.34 | |
2025.08 | 62 | 50.75 | |
2025.08 | 59.5 | 58.34 | |
2025.08 | 58 | 50.14 | |
2025.08 | 55.5 | 50.75 | |
2025.08 | 52 | 52.02 |