Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video-to-Text temporal grounding on ChronusAV
Loading...
63.15
Recall@IoU=0.5
ChronusOmni
-0.446
16.0645
32.575
49.0855
Dec 10, 2025
Recall@IoU=0.5
Recall@IoU=0.7
Updated 4mo ago
Evaluation Results
Method
Method
Links
Recall@IoU=0.5
Recall@IoU=0.7
ChronusOmni
Model Size=7B
2025.12
63.15
45.95
Qwen3-Omni
Model Size=30B-A3B
2025.12
37.85
21.8
ARC-Hunyuan-Video
Model Size=7B
2025.12
36.1
23.15
AVicuna
Model Size=7B
2025.12
10.75
4.7
LongVALE-LLM
Model Size=7B
2025.12
9.5
3.65
Qwen2.5-Omni
Model Size=7B
2025.12
7.05
3
Ola
Model Size=7B
2025.12
5.8
2.65
VideoLLaMA
Model Size=7B
2025.12
2
0.8
Feedback
Search any
task
Search any
task