                 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}{54.4} &                           57.9 &                           55.0 &                           73.5 &                           62.5 &                           66.7 &                           74.6 &                           61.3 &                           80.4 &                  \textbf{90.5} &                           82.0 &                           55.0 &                          100.0  \\
                               &     \scalebox{0.9}[1]{FgFactV} &                           57.6 & \cellcolor[RGB]{211,211,211}{55.4} &                           56.2 & \cellcolor[RGB]{211,211,211}{55.2} & \cellcolor[RGB]{211,211,211}{55.6} &                           60.0 &                           71.4 &                           59.2 &                           68.7 &                           80.0 &                 \textbf{100.0} &                           55.7 &                           95.5  \\
                               &      \scalebox{0.9}[1]{AnsCls} & \cellcolor[RGB]{211,211,211}{57.6} &                           59.3 & \cellcolor[RGB]{211,211,211}{57.8} &                           57.9 &                           66.7 &                           81.2 &                           76.5 &                           64.9 &                           70.0 &                           90.0 &                  \textbf{90.9} &                           57.9 &                           94.7  \\
                               &     \scalebox{0.9}[1]{MathGen} &                           80.5 &                           76.7 & \cellcolor[RGB]{211,211,211}{74.8} &                           91.2 &                  \textbf{96.9} &                           93.5 &                           81.2 & \cellcolor[RGB]{211,211,211}{74.8} &                           86.1 &                           93.5 &                           92.2 &                           75.0 &                          100.0  \\
                               &     \scalebox{0.9}[1]{FgFactV} &                           80.2 &                           80.1 &                           79.5 &                 \textbf{100.0} &                           80.0 &                          100.0 &                          100.0 &                           82.9 &                           98.7 &                           86.1 &                           94.2 &                           78.8 &                          100.0  \\
                               &      \scalebox{0.9}[1]{AnsCls} &                           80.9 & \cellcolor[RGB]{211,211,211}{77.1} &                           83.9 &                           79.5 & \cellcolor[RGB]{211,211,211}{66.7} &                 \textbf{100.0} &                          100.0 & \cellcolor[RGB]{211,211,211}{68.2} &                          100.0 &                           94.9 &                           96.1 &                           77.5 &                           96.7  \\
