
                    gpt-4-0613 &   math_word_problem_generation &                           51.8 &                           50.4 &                             -- &                             --  \\
                    gpt-4-0613 &  finegrained_fact_verification &                           68.4 &                           53.1 &                           59.1 &                             --  \\
                    gpt-4-0613 &   answerability_classification &                           62.5 &                             -- &                             -- &                           56.7  \\
           Llama-2-70b-chat-hf &   math_word_problem_generation &                           49.7 &                           50.5 &                             -- &                             --  \\
           Llama-2-70b-chat-hf &  finegrained_fact_verification &                           66.6 &                           63.0 &                           56.8 &                             --  \\
           Llama-2-70b-chat-hf &   answerability_classification &                           22.9 &                             -- &                             -- &                           24.7  \\
