 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} & 80.5 & 85.7 & \textbf{100.0} & \cellcolor[RGB]{211,211,211}{32.5} & \cellcolor[RGB]{211,211,211}{19.5} & \cellcolor[RGB]{211,211,211}{26.0} & 57.1 & 74.0 & 58.4 & \cellcolor[RGB]{211,211,211}{49.4} & 64.9 & 55.0 & 81.8 \\
 & \scalebox{0.9}[1]{FgFactV} & 67.9 & 92.3 & \textbf{98.7} & \cellcolor[RGB]{211,211,211}{20.5} & \cellcolor[RGB]{211,211,211}{51.3} & \cellcolor[RGB]{211,211,211}{11.5} & \cellcolor[RGB]{211,211,211}{38.5} & 57.7 & 59.0 & \cellcolor[RGB]{211,211,211}{5.1} & \cellcolor[RGB]{211,211,211}{14.1} & 55.7 & 95.5 \\
 & \scalebox{0.9}[1]{AnsCls} & 65.4 & \textbf{98.8} & 91.4 & \cellcolor[RGB]{211,211,211}{27.2} & \cellcolor[RGB]{211,211,211}{37.0} & \cellcolor[RGB]{211,211,211}{16.0} & \cellcolor[RGB]{211,211,211}{16.0} & \cellcolor[RGB]{211,211,211}{45.7} & \cellcolor[RGB]{211,211,211}{34.6} & \cellcolor[RGB]{211,211,211}{11.1} & \cellcolor[RGB]{211,211,211}{12.3} & 57.9 & 78.3 \\
 & \scalebox{0.9}[1]{MathGen} & 89.2 & 82.5 & \textbf{99.2} & \cellcolor[RGB]{211,211,211}{43.3} & \cellcolor[RGB]{211,211,211}{25.8} & \cellcolor[RGB]{211,211,211}{48.3} & \cellcolor[RGB]{211,211,211}{65.0} & \cellcolor[RGB]{211,211,211}{74.2} & 87.5 & 83.3 & 88.3 & 75.0 & 96.7 \\
 & \scalebox{0.9}[1]{FgFactV} & 80.2 & 89.7 & \textbf{92.1} & \cellcolor[RGB]{211,211,211}{10.3} & \cellcolor[RGB]{211,211,211}{44.4} & \cellcolor[RGB]{211,211,211}{6.3} & \cellcolor[RGB]{211,211,211}{17.5} & \cellcolor[RGB]{211,211,211}{46.0} & \cellcolor[RGB]{211,211,211}{60.3} & \cellcolor[RGB]{211,211,211}{24.6} & \cellcolor[RGB]{211,211,211}{51.6} & 78.8 & 100.0 \\
 & \scalebox{0.9}[1]{AnsCls} & \cellcolor[RGB]{211,211,211}{30.6} & \textbf{95.2} & 79.8 & \cellcolor[RGB]{211,211,211}{28.2} & \cellcolor[RGB]{211,211,211}{3.2} & \cellcolor[RGB]{211,211,211}{2.4} & \cellcolor[RGB]{211,211,211}{0.8} & \cellcolor[RGB]{211,211,211}{12.1} & \cellcolor[RGB]{211,211,211}{20.2} & \cellcolor[RGB]{211,211,211}{45.2} & \cellcolor[RGB]{211,211,211}{58.9} & 77.5 & 100.0 \\
