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

Video Reasoning on VBVR-Bench In-Domain

96Average Score

Human

25.2843.646280.36Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
9691.995.610095100
2026.03
787674.480.974.985.8
2026.03
7672.47578.274.583.3
2026.03
56.960.247.758.157.259.7
2026.03
53.161.150.35244.451
2026.03
41.24338.241.540.441.9
2026.03
40.846.532.337.534.751.9
2026.03
39.239.640.942.934.136.3
2026.03
32.931.636.232.63430.6
2026.03
28.324.132.825.732.830.5
2026.03
2820.735.729.32831.6