Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Young adult recidivism prediction on NLSY97 (1997-2002)
Loading...
71
Accuracy
gpt-4o-mini
32.52
42.51
52.5
62.49
Jan 29, 2026
Accuracy
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
gpt-4o-mini
Prompt=cot
2026.01
71
50
haiku-3.5
Prompt=cot
2026.01
71
0
haiku-3.5
Prompt=n-shot
2026.01
71
0
o3-mini
Prompt=n-shot
2026.01
70
70
sonnet-3.5
Prompt=n-shot
2026.01
57
72
o3-mini
Prompt=cot
2026.01
53
60
sonnet-3.5
Prompt=cot
2026.01
53
68
o3-mini
Prompt=zero-shot
2026.01
49
63
gpt-4o-mini
Prompt=zero-shot
2026.01
48
60
gpt-4o-mini
Prompt=n-shot
2026.01
47
49
sonnet-3.5
Prompt=zero-shot
2026.01
43
44
haiku-3.5
Prompt=zero-shot
2026.01
34
21
Feedback
Search any
task
Search any
task