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

Video Reasoning on TwiFF-Bench

3.11Avg CoT

FUTURE-L1-RL

1.99722.28612.5752.8639Feb 11, 2026Mar 1, 2026Mar 20, 2026Apr 8, 2026Apr 27, 2026May 16, 2026Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
3.11------2.973.04
2026.02
2.952.812.433.243.043.323.142.62-
2026.06
2.95------2.622.79
2026.02
2.92.762.343.133.033.343.112.55-
2026.06
2.9------2.552.73
2026.02
2.842.782.312.882.83.12.762.44-
2026.06
2.75------2.142.44
2026.06
2.62------2.422.52
2026.02
2.542.492.092.762.692.572.172.2-
2026.06
2.54------2.22.37
2026.02
2.462.41.642.571.772.641.411.63-
2026.06
2.46------1.632.05
2026.02
2.352.241.762.52.272.771.831.85-
2026.06
2.35------1.852.1
2026.02
2.292.21.722.452.12.612.221.85-
2026.06
2.29------1.852.07
2026.02
2.272.161.222.612.12.471.631.41-
2026.02
2.212.151.32.482.382.211.43-
2026.02
2.041.9512.141.362.380.931.04-
2026.06
2.04------1.041.54