Critique and Refinement Evaluation Dataset
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Critique and Refinement Evaluation Dataset Code
78.3CU Score
20
Critique and Refinement Evaluation Dataset Math
76.2CU Score
20
Critique and Refinement Evaluation Dataset
96.2CU Score
20
Critique and Refinement Evaluation Dataset Summarization
89.6CU
20
Critique and Refinement Evaluation Dataset Dialog
90.4CU Score
20