Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logical Reasoning on ProntoQA (val)
Loading...
98.01
Accuracy
CoT2
72.6756
79.2528
85.83
92.4072
May 29, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
CoT2
Backbone=4-layer, 4-he...
2025.05
98.01
COCONUT
Backbone=4-layer, 4-he...
2025.05
96.94
Discrete CoT
Backbone=4-layer, 4-he...
2025.05
82.47
Discrete no-CoT
Backbone=4-layer, 4-he...
2025.05
73.65
Feedback
Search any
task
Search any
task