Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
User behavior simulation on ML-100K
Loading...
71.99
Precision
STEAM
12.4916
27.9383
43.385
58.8317
Jan 23, 2026
Precision
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
F1 Score
STEAM
Ratio (1:k)=1:1
2026.01
71.99
63.93
AFL
Ratio (1:k)=1:1
2026.01
68.83
48.37
GPT-3.5-Turbo
Ratio (1:k)=1:1
2026.01
60.69
59.26
STEAM
Ratio (1:k)=1:3
2026.01
47.5
53.49
AFL
Ratio (1:k)=1:3
2026.01
35.8
45.26
GPT-3.5-Turbo
Ratio (1:k)=1:3
2026.01
34.11
43.96
STEAM
Ratio (1:k)=1:9
2026.01
21.65
31
AFL
Ratio (1:k)=1:9
2026.01
15.26
23.72
GPT-3.5-Turbo
Ratio (1:k)=1:9
2026.01
14.78
23.56
Feedback
Search any
task
Search any
task