Question Answering on HotpotQA (F1, Latency, Tokens)
78.7F1 Score
PageIndex
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 78.7 | 53 | 4,408 | |
2026.06 | 76.1 | 20 | 3,026 | |
2026.06 | 74.9 | 14 | 2,557 | |
2026.06 | 73.6 | 7,800 | 720 | |
2026.06 | 72.9 | 41 | 3,388 | |
2026.06 | 71.8 | 4,126 | 174 | |
2026.06 | 68.6 | 5,584 | 925 | |
2026.06 | 67.4 | 3,527 | 161 | |
2026.06 | 66.2 | 4,843 | 484 | |
2026.06 | 64.5 | 2,394 | 95 | |
2026.06 | 63.1 | 3,183 | 145 | |
2026.06 | 60.9 | 2,759 | 112 |