                 initial model &                        dataset &                    gemma-7b-it &            Llama-2-13b-chat-hf &            Llama-2-70b-chat-hf &     Mixtral-8x7B-Instruct-v0.1 &               Qwen1.5-14B-Chat &               Qwen1.5-72B-Chat &             gpt-3.5-turbo-0125 &             gemini-1.0-pro-001 &         claude-3-opus-20240229 &                     gpt-4-0613 &             gpt-4-0125-preview &                         random &                          human  \\
                               &     \scalebox{0.9}[1]{MathGen} & \cellcolor[RGB]{211,211,211}{18.6} & \cellcolor[RGB]{211,211,211}{37.1} &                           55.0 &                           55.7 &                           56.4 &                           58.6 &                           67.1 &                           55.7 &                           65.0 &                  \textbf{74.3} &                           68.6 &                           50.5 &                           88.2  \\
                               &     \scalebox{0.9}[1]{FgFactV} & \cellcolor[RGB]{211,211,211}{49.3} &                           55.0 &                           55.7 &                           53.6 &                           54.3 & \cellcolor[RGB]{211,211,211}{48.6} &                           57.9 &                           54.3 &                  \textbf{62.9} & \cellcolor[RGB]{211,211,211}{48.6} & \cellcolor[RGB]{211,211,211}{49.3} &                           50.7 &                           94.3  \\
                               &      \scalebox{0.9}[1]{AnsCls} &                           55.0 &                           58.6 &                           55.7 & \cellcolor[RGB]{211,211,211}{46.4} &                           55.0 & \cellcolor[RGB]{211,211,211}{47.9} & \cellcolor[RGB]{211,211,211}{47.1} &                  \textbf{62.1} & \cellcolor[RGB]{211,211,211}{50.7} & \cellcolor[RGB]{211,211,211}{50.0} & \cellcolor[RGB]{211,211,211}{50.0} &                           51.2 &                           82.9  \\
                               &     \scalebox{0.9}[1]{MathGen} & \cellcolor[RGB]{211,211,211}{25.0} & \cellcolor[RGB]{211,211,211}{58.1} &                           76.9 & \cellcolor[RGB]{211,211,211}{56.9} &                           81.9 &                           68.8 &                           75.6 &                           71.9 &                           78.1 &                  \textbf{84.4} &                           83.1 &                           62.5 &                           97.1  \\
                               &     \scalebox{0.9}[1]{FgFactV} &                           70.6 &                           78.1 &                           77.5 & \cellcolor[RGB]{211,211,211}{51.9} &                  \textbf{79.4} & \cellcolor[RGB]{211,211,211}{41.9} &                           67.5 & \cellcolor[RGB]{211,211,211}{57.5} & \cellcolor[RGB]{211,211,211}{55.6} & \cellcolor[RGB]{211,211,211}{41.2} & \cellcolor[RGB]{211,211,211}{63.1} &                           66.5 &                          100.0  \\
                               &      \scalebox{0.9}[1]{AnsCls} & \cellcolor[RGB]{211,211,211}{40.0} &                  \textbf{77.5} &                           71.2 & \cellcolor[RGB]{211,211,211}{36.9} &                           76.2 & \cellcolor[RGB]{211,211,211}{26.2} & \cellcolor[RGB]{211,211,211}{25.0} & \cellcolor[RGB]{211,211,211}{32.5} & \cellcolor[RGB]{211,211,211}{36.9} & \cellcolor[RGB]{211,211,211}{57.5} &                           68.8 &                           65.1 &                           97.1  \\
