Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Explanation self-consistency on ARC-E (test)
Loading...
87.01
Accuracy
PSCB
80.4372
82.1436
83.85
85.5564
Jun 9, 2025
Accuracy
CC-Cos (Worst)
CC-Cos (Mean)
CC-Cos (Best)
CC-Sp (Worst)
CC-Sp (Mean)
CC-Sp (Best)
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
CC-Cos (Worst)
CC-Cos (Mean)
CC-Cos (Best)
CC-Sp (Worst)
CC-Sp (Mean)
CC-Sp (Best)
PSCB
Model=LLaMA3.1-8B, Att...
2025.06
87.01
13.31
14.16
15.02
1.06
12.44
25.77
PSCB
Model=LLaMA3.1-8B, Att...
2025.06
82.87
1.49
1.78
2.07
38.81
46.42
53.41
PSCB
Model=LLaMA3.2-3B, Att...
2025.06
81.9
5.32
5.86
6.41
7.26
19.68
31.98
PSCB
Model=LLaMA3.2-3B, Att...
2025.06
80.69
1.65
2.04
2.41
36.63
45.58
53.68
Feedback
Search any
task
Search any
task