Model,Agent,Opponent Model,Opponent Agent,Tic-Tac-Toe,Connect Four,Breakthrough,Liar's Dice,Blind Auction,Negotiation,Kuhn Poker,Nim,Pig,Iterated Prisoner's Dilemma, GPT-3.5-turbo,Prompt,GPT-3.5-turbo-1106,prompt agent,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000 GPT-4,Prompt,GPT-3.5-turbo-1106,prompt agent,-0.111,0.080,0.320,0.800,0.040,-0.281,0.400,0.080,-0.040,0.004,0.129 GPT-4,CoT,GPT-3.5-turbo-1106,prompt agent,-0.022,-0.080,0.560,0.240,0.069,0.135,0.440,0.040,0.040,-0.160,0.126 GPT-3.5-turbo,CoT,GPT-3.5-turbo-1106,prompt agent,0.277,-0.320,-0.120,0.440,0.115,-0.207,0.120,-0.040,-0.160,0.126,0.023 GPT-3.5-turbo,SC-CoT,GPT-3.5-turbo-1106,prompt agent,0.409,-0.040,-0.160,0.520,-0.120,-0.315,-0.080,0.000,-0.080,-0.155,-0.002 GPT-3.5-turbo,ToT,GPT-3.5-turbo-1106,prompt agent,-0.045,0.240,0.160,0.000,-0.120,0.183,0.000,0.120,-0.400,-0.191,-0.005 Codellama-34b-instruct,Prompt,GPT-3.5-turbo-1106,prompt agent,0.333,-0.100,-0.800,-0.400,-0.250,0.216,-0.160,0.360,0.120,0.600,-0.008 Llama-2-70b-chat,SC-CoT,GPT-3.5-turbo-1106,prompt agent,-0.469,-0.160,-0.680,0.160,-0.040,0.052,0.120,0.040,0.040,0.296,-0.064 Codellama-34b-instruct,CoT,GPT-3.5-turbo-1106,prompt agent,0.316,-0.360,-0.760,-0.320,-0.268,0.085,0.000,0.480,-0.080,0.032,-0.088 Llama-2-70b-chat,CoT,GPT-3.5-turbo-1106,prompt agent,-0.500,0.080,-0.800,0.265,-0.086,0.128,-0.200,0.061,-0.160,0.324,-0.089 Mistral-7b-Orca,CoT,GPT-3.5-turbo-1106,prompt agent,-0.077,-0.120,-0.320,-0.560,0.133,0.078,0.000,0.360,-0.680,0.055,-0.113 Codellama-34b-instruct,SC-CoT,GPT-3.5-turbo-1106,prompt agent,0.122,-0.600,-0.560,-0.280,-0.348,0.095,0.000,0.160,0.120,0.008,-0.128 Mistral-7b-Orca,SC-CoT,GPT-3.5-turbo-1106,prompt agent,-0.200,-0.080,-0.400,-0.640,0.082,0.364,-0.040,0.440,-0.840,0.013,-0.130 Codellama-34b-instruct,ToT,GPT-3.5-turbo-1106,prompt agent,-0.021,-0.160,-0.600,-0.520,-0.304,0.098,0.000,-0.040,-0.160,0.237,-0.147 Llama-2-70b-chat,Prompt,GPT-3.5-turbo-1106,prompt agent,-0.366,-1.000,-0.440,-0.160,-0.075,-0.033,-0.040,0.800,-0.020,-0.712,-0.205 Mistral-7b-Orca,ToT,GPT-3.5-turbo-1106,prompt agent,-0.179,-0.800,-0.320,-0.440,-0.047,0.299,-0.200,-0.080,-0.840,0.162,-0.245 Mistral-7b-Orca,Prompt,GPT-3.5-turbo-1106,prompt agent,-0.429,-0.840,-0.680,-0.680,-0.069,-0.114,-0.040,-0.080,0.000,-0.182,-0.311 GPT-4,Prompt,GPT-4,prompt agent,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000 Codellama-34b-instruct,Prompt,GPT-4,prompt agent,-0.064,0.720,-0.600,-0.640,-0.148,0.000,0.080,0.160,0.040,0.342,-0.011 Codellama-34b-instruct,CoT,GPT-4,prompt agent,0.022,0.560,-1.000,-0.800,0.449,-0.078,0.080,0.200,-0.080,0.224,-0.042 Llama-2-70b-chat,Prompt,GPT-4,prompt agent,-0.938,0.960,-0.920,-0.720,-0.250,0.000,-0.040,0.360,0.200,0.333,-0.101 Llama-2-70b-chat,CoT,GPT-4,prompt agent,-0.286,0.200,-0.880,-0.917,-0.417,0.201,0.000,-0.026,-0.360,0.173,-0.231