Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Needle-in-a-Haystack on Haystack-LVBench
Loading...
2.8
Precision
CogniGPT
1.136
1.568
2
2.432
Sep 29, 2025
Precision
Recall
F1 Score
Updated 27d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
CogniGPT
Frames=10.7
2025.09
2.8
10.6
4.4
CogniGPT w/o Verification
Frames=7.8
2025.09
2.3
8.9
3.7
T*
Frames=8.0
2025.09
1.6
7.1
2.5
VideoAgent*
Frames=10.1
2025.09
1.2
8.5
2.1
Feedback
Search any
task
Search any
task