Web-based Question Answering on BrowseComp-plus
78.41Accuracy
GPT5/MixedbreadSearch
Updated 7d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 78.41 | 48.85 | 44.67 | - | |
2026.01 | 71.69 | 78.98 | 21.74 | - | |
2026.01 | 66.6 | 76.6 | 21.74 | - | |
2026.01 | 65.9 | 73.24 | 23.97 | - | |
2026.01 | 64.92 | 68.07 | 46.99 | - | |
2026.01 | 57.59 | 61.7 | 23.23 | - | |
2026.01 | 44.46 | 62.32 | 30.37 | - | |
2025.07 | 37.35 | 47.33 | 9.03 | - | |
2025.07 | 36.75 | 50.84 | 10.24 | - | |
2025.07 | 35.42 | 38.38 | 11.22 | - | |
2025.07 | 35.06 | 49.29 | 23.87 | - | |
2025.07 | 34.58 | 40.19 | 9.77 | - | |
2025.07 | 30.48 | 41.31 | 13.64 | - | |
2025.07 | 29.52 | 35.31 | 6.04 | - | |
2025.07 | 25.54 | 22.5 | 2.21 | - | |
| 21.53 | 22.93 | 10.96 | - | ||
| 21.14 | 23.73 | 8.39 | - | ||
| 20.46 | 23.57 | 7.95 | - | ||
2025.07 | 16.39 | 16.32 | 2.72 | - | |
2025.07 | 14.1 | 17.37 | 1.87 | - | |
2025.07 | 11.08 | 10.17 | 1.69 | - | |
2025.07 | 10.72 | 7.8 | 0.94 | - | |
| - | - | - | 0 | ||
2026.05 | - | - | - | 0 | |
2026.05 | - | - | - | 81.7 | |
| - | - | - | 0 | ||
2026.05 | - | - | - | 6.6 | |
2026.05 | - | - | - | 26.9 | |
2026.05 | - | - | - | 88 | |
| - | - | - | 0 | ||
2026.05 | - | - | - | 1.1 | |
2026.05 | - | - | - | 29.7 | |
2026.05 | - | - | - | 41.9 | |
2026.05 | - | - | - | 91 |