Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
PKU-SafeRLHF
Report a problem with this record
anchor
Findings
IC-159
GPT-4o achieves 55.6% accuracy on creation, 74.8% on math, and 68.1% on code as a preference judge, and is outperformed by domain-specific 7B models on those tasks
[eval]