Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Quiz Evaluation on SciVidEval
Loading...
99.5
VLM-as-Judge Score
Source Paper
84.94
88.72
92.5
96.28
Sep 14, 2025
VLM-as-Judge Score
Human Evaluation Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
VLM-as-Judge Score
Human Evaluation Score
Source Paper
2025.09
99.5
95
VideoAgent
Backbone=Gemini-2.5 Pr...
2025.09
99.5
87.5
NotebookLM
2025.09
99
86
VideoAgent
Backbone=GPT-4o, Summa...
2025.09
99
-
AutoSlides
2025.09
98.5
78
VideoAgent
Backbone=Qwen-2.5VL-7B...
2025.09
98
-
Author
2025.09
97
90
PresentAgent
2025.09
97
75
LunWenShuo
2025.09
89.5
79.5
Pictory
2025.09
85.5
74
Feedback
Search any
task
Search any
task