Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Narration Quality Evaluation on SciVidEval
Loading...
16.67
Perplexity (PPL)
NotebookLM
16.3096
18.7423
21.175
23.6077
Sep 14, 2025
Perplexity (PPL)
ROUGE-L
LLM Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Perplexity (PPL)
ROUGE-L
LLM Judge Score
NotebookLM
2025.09
16.67
7
8.76
Source Paper
2025.09
17.46
100
10
VideoAgent
Backbone=GPT-4o, Summa...
2025.09
18.08
16
9.38
VideoAgent
Backbone=Gemini-2.5 Pr...
2025.09
18.32
14
9.7
VideoAgent
Backbone=Qwen-2.5VL-7B...
2025.09
18.42
8
9.31
LunWenShuo
2025.09
22.76
12
8.6
Author
2025.09
23.93
11
8.13
Pictory
2025.09
25.68
6
9
Feedback
Search any
task
Search any
task