Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Accuracy on Research Questions
Loading...
0.8021
Preference Accuracy
DICAI
0.496028
0.575489
0.65495
0.734411
Jun 26, 2026
Preference Accuracy
Updated 27d ago
Evaluation Results
Method
Method
Links
Preference Accuracy
DICAI
Judge Model=GPT-4o
2026.06
0.8021
ICAI
Judge Model=GPT-4o
2026.06
0.702
CoT
Judge Model=GPT-4o
2026.06
0.568
Self-Refine
Judge Model=GPT-4o
2026.06
0.5379
ToT
Judge Model=GPT-4o
2026.06
0.5355
AutoRubric
Judge Model=GPT-4o
2026.06
0.5355
CoT-SC
Judge Model=GPT-4o
2026.06
0.5078
Feedback
Search any
task
Search any
task