Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Reconstruction on Consequences
Loading...
75.23
Preference Accuracy
DICAI
46.1204
53.6777
61.235
68.7923
Jun 26, 2026
Preference Accuracy
Updated 27d ago
Evaluation Results
Method
Method
Links
Preference Accuracy
DICAI
Judge LLM=GPT-5
2026.06
75.23
DICAI
Judge Model=GPT-4o
2026.06
73.21
ICAI
Judge LLM=GPT-5
2026.06
67.8
ICAI
Judge Model=GPT-4o
2026.06
61.2
AutoRubric
Judge LLM=GPT-5
2026.06
56.77
CoT
Judge LLM=GPT-5
2026.06
54.56
Self-Refine
Judge LLM=GPT-5
2026.06
52.51
AutoRubric
Judge Model=GPT-4o
2026.06
52.44
ToT
Judge LLM=GPT-5
2026.06
52.27
Self-Refine
Judge Model=GPT-4o
2026.06
51.1
CoT-SC
Judge LLM=GPT-5
2026.06
50.33
CoT
Judge Model=GPT-4o
2026.06
48.29
ToT
Judge Model=GPT-4o
2026.06
47.4
CoT-SC
Judge Model=GPT-4o
2026.06
47.24
Feedback
Search any
task
Search any
task