Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Reasoning on LegalBench (Comprehensive Metrics)
Loading...
82.3
Accuracy
QwQ-32B
75.956
77.603
79.25
80.897
Jun 2, 2026
Accuracy
Decision Accuracy
CR Score
CD Score
CS Score
cMFG (R)
cMFG (D)
cMFG (S)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Decision Accuracy
CR Score
CD Score
CS Score
cMFG (R)
cMFG (D)
cMFG (S)
QwQ-32B
Model Type=Natively-tr...
2026.06
82.3
62.4
76.6
73.7
80.9
74.7
77.2
71.2
DeepSeek-R1-8B
Model Type=Distilled L...
2026.06
76.2
66.6
69.9
67.4
74.6
77.9
79.3
67.8
Feedback
Search any
task
Search any
task