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

Video Understanding and Reasoning on Video-MMMU (test)

0.612Accuracy

GPT-4o

0.191840.300920.410.51908Nov 14, 2025Dec 10, 2025Jan 6, 2026Feb 1, 2026Feb 28, 2026Mar 26, 2026Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
0.612----
2025.11
0.55----
2025.11
0.54----
2026.04
0.524----
2025.11
0.523----
2026.04
0.523----
2025.11
0.519----
2026.04
0.513----
2025.11
0.511----
2025.11
0.51----
2026.04
0.51----
2026.04
0.505----
2026.04
0.504----
2026.04
0.498----
2026.04
0.494----
2026.04
0.494----
2026.04
0.487----
2026.04
0.483----
2025.11
0.481----
2026.04
0.481----
2026.04
0.478----
2026.04
0.474----
2026.04
0.471----
2026.04
0.465----
2025.11
0.338----
2026.04
0.338----
2025.11
0.239----
2026.04
0.239----
2026.04
0.208----
2025.12
-0.4570.560.50.31
2025.12
-0.4550.5830.480.301
2025.12
-0.4470.5470.4770.316
2025.12
-0.4550.5930.4650.305
2025.12
-0.4760.5970.5130.317
2025.12
-0.4860.640.4730.343
2025.12
-0.4630.620.4630.307
2025.12
-0.4660.6370.4430.317
2025.12
-0.4750.640.4570.33
2025.12
-0.5190.660.5070.39
2025.12
-0.240.2670.1890.263
2025.12
-0.2280.270.180.233
2025.12
-0.2380.2730.1670.273
2025.12
-0.2440.2370.2030.293
2025.12
-0.2510.2710.220.263