Multimodal Humor Explanation on New Yorker
76.7Precision
COT
Updated 5mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.02 | 76.7 | 13.1 | 22.3 | |
2025.02 | 76.6 | 24.1 | 36.6 | |
2025.02 | 76.2 | 24.1 | 36.7 | |
2025.02 | 76 | 26.1 | 38.8 | |
2025.02 | 75.4 | 42 | 53.9 | |
2025.02 | 75.2 | 45.8 | 56.9 | |
2025.02 | 75.1 | 44.6 | 56 | |
2025.02 | 74.5 | 47.7 | 58.2 | |
2025.02 | 74 | 21.2 | 32.9 | |
2025.02 | 73.7 | 22.9 | 34.9 | |
2025.02 | 70.9 | 11 | 19 | |
2025.02 | 68.4 | 17.7 | 28.1 | |
2025.02 | 67.4 | 17.8 | 28.2 | |
2025.02 | 67.3 | 18.6 | 29.1 | |
2025.02 | 66.7 | 19.4 | 30.1 | |
2025.02 | 57.4 | 8.5 | 14.8 | |
2025.02 | 55.8 | 15 | 23.6 | |
2025.02 | 51.2 | 14.8 | 23 | |
2025.02 | 51.2 | 15.1 | 23.3 | |
2025.02 | 49.1 | 13 | 20.6 |