Open-Ended Question Answering on SAGE Web Search
35.1Weighted Recall (Com. Sci.)
GPT-5
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.02 | 35.1 | 25 | 18.8 | 26.2 | 26.3 | |
2026.02 | 28.9 | 33.5 | 36.6 | 33 | 33 | |
2026.02 | 28.2 | 10.1 | 15.7 | 9.8 | 16 | |
2026.02 | 27.4 | 17.8 | 13.9 | 22.4 | 20.4 | |
2026.02 | 25.9 | 29.8 | 15.7 | 21.1 | 20.6 | |
2026.02 | 22.4 | 26.3 | 29.3 | 26.2 | 26 | |
2026.02 | 20.3 | 36.2 | 34 | 32.3 | 30.7 | |
2026.02 | 20 | 5.2 | 12.2 | 6.7 | 11 | |
2026.02 | 18.2 | 29.4 | 28.3 | 26.3 | 25.5 | |
2026.02 | 18 | 17.2 | 14.1 | 20.2 | 17.4 | |
2026.02 | 16.1 | 29.5 | 32 | 27.4 | 26.2 | |
2026.02 | 11.3 | 18.5 | 22.3 | 17 | 17.3 |