Preference Prediction on VLRM-Bench
80.25Preference Prediction Score (k=99)
PRISM
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.06 | 80.25 | 80.82 | 80.11 | 80.04 | 78.64 | 77.16 | 64.09 | 78.78 | |
2026.06 | 79.24 | 79.86 | 79.17 | 79.1 | 77.71 | 76.25 | 63.33 | 77.78 | |
2026.06 | 78.36 | 79.9 | 79.48 | 79.48 | - | 76.11 | 63.81 | 77.86 | |
2026.06 | 77.43 | 78.96 | 78.54 | 78.54 | 76.94 | 75.21 | 63.06 | 76.88 | |
2026.06 | 77.37 | 77.09 | 76.18 | 75.61 | 69.5 | 67.25 | 52.21 | 77.09 | |
2026.06 | 76.46 | 76.18 | 75.28 | 74.72 | 68.68 | 66.46 | 51.6 | 76.18 | |
2026.06 | 68.02 | 59.03 | 48.91 | 22.55 | 19.53 | 20.81 | 21.43 | 67.81 | |
2026.06 | 67.22 | 58.33 | 48.33 | 22.77 | 19.86 | 21.11 | 21.66 | 67.01 | |
2026.06 | 65.35 | 64.58 | 53.83 | 52.91 | 53.26 | 53.34 | 54.53 | 69.29 | |
2026.06 | 64.58 | 63.82 | 53.12 | 52.22 | 52.56 | 52.71 | 53.89 | 68.47 | |
2026.06 | 56.43 | 51.23 | 33.38 | 16.51 | 19.82 | 20.03 | 18.55 | 56.78 | |
2026.06 | 53.47 | 49.44 | 28.89 | 9.58 | 8.54 | 11.04 | 12.01 | 55.21 |