Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-choice Video Question Answering on EgoSchema (test)

72.2Accuracy

GPT4-O

17.91232.00646.160.194Apr 9, 2024Jun 25, 2024Sep 10, 2024Nov 27, 2024Feb 12, 2025Apr 30, 2025Jul 17, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2024.12
72.2
2025.07
67.6
2024.12
63.9
2024.12
63.2
2024.12
62
2024.12
60.9
60.1
2025.07
58
57.3
2024.12
55.7
2024.12
55.6
2024.12
51.7
2024.04
51.7
2025.07
51.6
51.5
50.5
2024.04
49.9
2024.04
49.3
2024.12
46.5
2024.12
43.9
2024.12
42.2
2024.04
41
2024.12
38.5
2024.12
38.4
2024.12
37.3
20