Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Deductive, Inductive, Abductive)
Loading...
79.37
Deductive Accuracy
Complementary S.
76.1356
76.9753
77.815
78.6547
Apr 26, 2026
Deductive Accuracy
Inductive Accuracy
Abductive Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Deductive Accuracy
Inductive Accuracy
Abductive Accuracy
Complementary S.
Backbone=Llama-3.1-8B-it
2026.04
79.37
78.33
78.62
Mono S.
Backbone=Llama-3.1-8B-it
2026.04
78.31
77.75
78.24
Unsteered
Backbone=Llama-3.1-8B-it
2026.04
76.26
76.26
76.26
Feedback
Search any
task
Search any
task