Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Behavior Prediction on Carat Top 1000 Users App Usage Dataset (test)
Loading...
44.7
Weighted Precision
BUA
29.308
33.304
37.3
41.296
Apr 26, 2026
Weighted Precision
Weighted Recall
Overall Score
Head Category Score
Medium Category Score
Tail Category Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Weighted Precision
Weighted Recall
Overall Score
Head Category Score
Medium Category Score
Tail Category Score
BUA
2026.04
44.7
41.8
40
40.9
45.1
26.7
CoLLM
2026.04
40
36.5
36.7
37.7
41.8
23.3
PITuning
2026.04
35.2
35.6
35.7
36.2
42.5
15.2
BehaveGPT
2026.04
29.9
31.8
21
30.3
21.9
5.2
Feedback
Search any
task
Search any
task
