Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Math Book

Benchmarks

Task NameDataset NameSOTA ResultTrend
Chain-of-Thought Faithfulness EvaluationMath Book
Unfaithful Explanation Rate22.8
14
Explanation Faithfulness EvaluationMath Book (test)
Greedy Score31.4
7
Showing 2 of 2 rows