Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Temporal Understanding on TempCompass and TVBench

0.738TempCompass Score

GPT-4o

0.668320.686410.70450.72259Dec 4, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
0.7380.3990.569
2025.12
0.7370.4770.607
2025.12
0.7340.4610.598
2025.12
0.7320.4690.601
2025.12
0.7290.4670.598
2025.12
0.7260.4940.61
2025.12
0.7110.4640.588
2025.12
0.7030.4520.578
2025.12
0.70.4520.576
2025.12
0.6990.4550.577
2025.12
0.6970.4520.575
2025.12
0.6950.4510.573
2025.12
0.6930.430.561
2025.12
0.6850.4290.557
2025.12
0.6830.4280.556
2025.12
0.6830.4290.556
2025.12
0.6710.4760.574