Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Explanation self-consistency on ARC-C (test)
Loading...
77.57
Accuracy
PSCB
64.3932
67.8141
71.235
74.6559
Jun 9, 2025
Accuracy
Worst Case Cosine Correlation
Mean Cosine Correlation
Best Cosine Correlation
Worst Spearman Correlation
Mean Spearman Correlation
Best Spearman Correlation
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Worst Case Cosine Correlation
Mean Cosine Correlation
Best Cosine Correlation
Worst Spearman Correlation
Mean Spearman Correlation
Best Spearman Correlation
PSCB
Model=LLaMA3.1-8B, Att...
2025.06
77.57
15.09
16.07
17.08
1.82
11.48
24.73
PSCB
Model=LLaMA3.1-8B, Att...
2025.06
71.12
1.39
1.67
1.94
37.07
44.87
52.11
PSCB
Model=LLaMA3.2-3B, Att...
2025.06
68.7
7.67
8.29
8.93
5.94
18.44
30.89
PSCB
Model=LLaMA3.2-3B, Att...
2025.06
64.9
1.49
1.9
2.29
33.22
41.43
49.12
Feedback
Search any
task
Search any
task