{"$k":["studySlug","chartId","series","point","metric","label","value","unit","display","n","ci","spanKind","context"],"$r":[["swe-bench-verified","swebench-same-instance-leaderboard","Resolved rate","GPT 5.2 (high)","swebench-same-instance-leaderboard","Resolved rate on the same 33 SWE-bench Verified instances",0.8485,"rate","85% (28/33)",33,[0.6908,0.9335],"ci95","effort high · public mini-SWE-agent v2 run, same instances"],["swe-bench-verified","swebench-model-calls","Mean calls","GPT 5.2 (high)","swebench-model-calls","Model calls per instance",35.6,"calls","35.6",33,"\u0001","\u0001","effort high · public mini-SWE-agent v2 run, same instances"],["cost-thought-experiments","cost-per-resolved-agent-vs-panel","Cost per resolved instance","GPT 5.2 (high)","cost-per-resolved-agent-vs-panel","Recorded cost per resolved instance: Agent vs the public panel",0.628,"usd","$0.63",28,"\u0001","\u0001","effort high · public mini-SWE-agent v2 run, same instances"]]}