Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
DeepSeek R1
Report a problem with this record
text · generative, reinforcement-learning ·
anchor
Findings
IC-096
Large commercial and open-weight models achieve 70-78% accuracy on CASELAWQA, with Claude 3.7 Sonnet at the top