{"$k":["studySlug","chartId","series","point","metric","label","value","unit","display","n","ci","spanKind","context"],"$r":[["swe-bench-verified","swebench-same-instance-leaderboard","Resolved rate","MiniMax M2.5 (high)","swebench-same-instance-leaderboard","Resolved rate on the same 33 SWE-bench Verified instances",0.697,"rate","70% (23/33)",33,[0.5266,0.8262],"ci95","effort high · public mini-SWE-agent v2 run, same instances"],["swe-bench-verified","swebench-model-calls","Mean calls","MiniMax M2.5 (high)","swebench-model-calls","Model calls per instance",58.4,"calls","58.4",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","MiniMax M2.5 (high)","cost-per-resolved-agent-vs-panel","Recorded cost per resolved instance: Agent vs the public panel",0.107,"usd","$0.11",23,"\u0001","\u0001","effort high · public mini-SWE-agent v2 run, same instances"]]}