                 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}{54.2} &                           60.3 &                           59.8 &                           72.5 &                           75.0 &                           71.4 &                           63.3 &                           56.2 &                  \textbf{95.8} &                           89.6 &                           80.6 &                           55.0 &                          100.0  \\
                               &     \scalebox{0.9}[1]{FgFactV} & \cellcolor[RGB]{211,211,211}{53.3} & \cellcolor[RGB]{211,211,211}{49.4} &                           56.9 &                           64.1 &                           56.6 &                           65.2 & \cellcolor[RGB]{211,211,211}{55.6} &                           57.6 &                           65.5 &                  \textbf{85.7} &                           73.3 &                           55.7 &                           95.5  \\
                               &      \scalebox{0.9}[1]{AnsCls} &                           58.9 &                           58.5 & \cellcolor[RGB]{211,211,211}{56.7} &                           60.0 &                           59.6 &                           71.4 &                           63.9 &                           76.9 &                           75.0 &                  \textbf{92.3} &                           91.7 &                           57.9 &                           94.7  \\
                               &     \scalebox{0.9}[1]{MathGen} &                           76.8 & \cellcolor[RGB]{211,211,211}{70.6} &                           85.6 &                           84.3 &                           91.7 &                           93.1 &                           83.5 &                           93.9 &                  \textbf{94.3} &                           93.6 &                           89.1 &                           75.0 &                          100.0  \\
                               &     \scalebox{0.9}[1]{FgFactV} &                           86.2 &                           80.2 &                           81.1 &                           96.3 &                           82.4 &                 \textbf{100.0} &                           96.0 &                           84.2 &                          100.0 &                           90.0 &                           93.2 &                           78.8 &                          100.0  \\
                               &      \scalebox{0.9}[1]{AnsCls} & \cellcolor[RGB]{211,211,211}{76.1} &                           79.4 &                           79.4 & \cellcolor[RGB]{211,211,211}{75.6} &                           78.6 &                 \textbf{100.0} &                          100.0 &                           80.0 &                          100.0 &                           94.1 &                           91.2 &                           77.5 &                           96.7  \\
