Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Reasoning on Real-World Trust
Loading...
90
Accuracy
LegalDrill 1.7B
73.36
77.68
82
86.32
Apr 26, 2026
Accuracy
F1 Score
Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Judge Score
LegalDrill 1.7B
Distillation Source=GP...
2026.04
90
60
70
GPT-4o
2026.04
89
60
73
LegalDrill 0.6B
Distillation Source=GP...
2026.04
86
58
69
Qwen3-1.7B
Backbone=1.7B
2026.04
79
54
51
Qwen3-0.6B
Backbone=0.6B
2026.04
74
49
44
Feedback
Search any
task
Search any
task