Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Entailment on Privacy Policy Entailment (Priv. Ent.)
Loading...
85
Accuracy
LegalDrill-1.7B
-2.36
20.32
43
65.68
Apr 26, 2026
Accuracy
F1 Score
Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Judge Score
LegalDrill-1.7B
Evaluation Protocol=Di...
2026.04
85
80
59
Qwen3-30B-A3B-Instruct
Evaluation Protocol=Ze...
2026.04
83
75
65
LegalDrill-0.6B
Evaluation Protocol=Di...
2026.04
81
80
58
DeepSeek ESFT-16B
Evaluation Protocol=Ze...
2026.04
75
64
73
GPT-4o
Evaluation Protocol=Ze...
2026.04
67
30
60
Law-LLM-13B
Evaluation Protocol=Ze...
2026.04
64
38
29
LegalDrill-1.7B
Evaluation Protocol=Di...
2026.04
60
31
52
LegalDrill-0.6B
Evaluation Protocol=Di...
2026.04
59
32
52
Qwen3-1.7B
Evaluation Protocol=Ze...
2026.04
47
45
30
Qwen3-0.6B
Evaluation Protocol=Ze...
2026.04
30
29
24
DiscLaw-13B
Evaluation Protocol=Ze...
2026.04
1
1
1
Feedback
Search any
task
Search any
task