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

Video Reasoning on STAR

67.7Score

BoxTuning

56.67659.53862.465.262Oct 27, 2025Nov 24, 2025Dec 22, 2025Jan 19, 2026Feb 16, 2026Mar 16, 2026Apr 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
67.7
2026.04
67.2
2026.04
67.1
2026.04
64.9
2025.10
62.45
2025.10
62.33
2025.10
62.29
2025.10
62.19
2025.10
61.65
2025.10
61.51
2025.10
61.21
2025.10
59.48
2025.10
58.3
2025.10
58.28
58.07
2025.10
57.94
2025.10
57.79
2025.10
57.2
2026.04
57.1