Vision-Language Reasoning on SugarCrepe (test)
62.75Simple Accuracy
Q4 system redistr (prop)
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 62.75 | 25.93 | 85.71 | |
2026.01 | 58.79 | 17.58 | 90.66 | |
2026.01 | 58.18 | 16.37 | 91.37 | |
2026.01 | 57.97 | 16.04 | 91.59 | |
2026.01 | 57.53 | 15.16 | 92.03 | |
2026.01 | 57.47 | 15.05 | 91.98 | |
2026.01 | 57.14 | 14.4 | 92.53 |