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

WorldSense

Benchmarks

Task NameDataset NameSOTA ResultTrend
Audio-visual understandingWorldSense
Accuracy66.4
72
Video UnderstandingWorldSense
Score52.01
33
Audio-Visual ReasoningWorldSense
Score54.3
32
Audio-Visual PerceptionWorldSense
Score47.4
26
Omnimodal UnderstandingWorldSense v1.0 (test)
Tech & Science Score52.65
24
Video Question AnsweringWorldSense
Accuracy54
24
Multimodal Fact-Level AttributionWorldSense 1.0 (sampled examples)
Accuracy71.4
24
Common Sense ReasoningWorldSense
Accuracy64.6
19
Long Audio-Video Question AnsweringWorldSense
Average Accuracy61.2
18
Audio-visual Question AnsweringWorldSense
Accuracy50
18
Multi-modal UnderstandingWorldSense
WorldSense Performance46.85
14
Long Video ReasoningWorldSense
Overall Accuracy52.5
13
Omni-modal UnderstandingWorldSense
Accuracy48
12
Video Question AnsweringWorldSense
Accuracy (Tech & Science)48.78
10
Omnimodal UnderstandingWorldSense (test)
Tech & Science Score54.7
9
Long-form audio-video understandingWorldSense up to 10min (Avg.)
Avg Performance (WorldSense)52.6
8
Video UnderstandingWorldSense
TFLOPs12
8
Video UnderstandingWorldSense (test)
Overall Accuracy42.6
8
Video ReasoningWorldSense
Accuracy40.4
7
Commonsense ReasoningWorldSense
Overall Score42.6
7
Audio-Visual Understanding and ReasoningWorldSense
AVG48
6
Audio-Visual QuestionWorldSense
Accuracy (Clean)59.7
6
Video Grounded ReasoningWorldSense
Original Score45.4
6
Visual Question AnsweringWorldSense sampled examples 1.0
Accuracy60
4
Text Query QAWorldSense
Score65.5
3
Showing 25 of 26 rows