{"$k":["studySlug","chartId","series","point","metric","label","value","unit","display","n","ci","spanKind","context"],"$r":[["swe-bench-verified","swebench-same-instance-leaderboard","Resolved rate","GPT 5 mini","swebench-same-instance-leaderboard","Resolved rate on the same 33 SWE-bench Verified instances",0.6364,"rate","64% (21/33)",33,[0.4662,0.7781],"ci95","public mini-SWE-agent v2 run, same instances"],["swe-bench-verified","swebench-model-calls","Mean calls","GPT 5 mini","swebench-model-calls","Model calls per instance",20.8,"calls","20.8",33,"\u0001","\u0001","public mini-SWE-agent v2 run, same instances"],["cost-thought-experiments","cost-per-resolved-agent-vs-panel","Cost per resolved instance","GPT 5 mini","cost-per-resolved-agent-vs-panel","Recorded cost per resolved instance: Agent vs the public panel",0.08,"usd","$0.080",21,"\u0001","\u0001","public mini-SWE-agent v2 run, same instances"]]}