
                    gpt-4-0613 &   math_word_problem_generation &                           47.3 &                           49.6 &                             -- &                             --  \\
                    gpt-4-0613 &  finegrained_fact_verification &                           71.3 &                           53.1 &                           57.7 &                             --  \\
                    gpt-4-0613 &   answerability_classification &                           63.4 &                             -- &                             -- &                           52.1  \\
           Llama-2-70b-chat-hf &   math_word_problem_generation &                           50.0 &                           49.3 &                             -- &                             --  \\
           Llama-2-70b-chat-hf &  finegrained_fact_verification &                           64.0 &                           63.4 &                           58.6 &                             --  \\
           Llama-2-70b-chat-hf &   answerability_classification &                           47.1 &                             -- &                             -- &                           43.3  \\
