{"i":0,"slug":"swe-bench-verified","chart":{"id":"swebench-views","title":"Every way to slice the run, with intervals","subtitle":"Agent resolved rate and 95% Wilson interval per declared view","kind":"dot-range","unit":"rate","yLabel":"Resolved","series":[{"name":"Agent","points":{"$k":["label","value","lo","hi","n","highlight"],"$r":[["Campaign 1: 25-instance sample",0.72,0.5242,0.8572,25,"\u0001"],["Campaign 2: 8 compiled-extension instances",0.875,0.5291,0.9776,8,"\u0001"],["Original seed draw of 25",0.76,0.5657,0.885,25,"\u0001"],["All 33 attempted",0.7576,0.5898,0.8717,33,true]]}},{"name":"Public panel mean, same instances","points":{"$k":["label","value","n"],"$r":[["Campaign 1: 25-instance sample",0.7091,25],["Campaign 2: 8 compiled-extension instances",0.8409,8],["Original seed draw of 25",0.7091,25],["All 33 attempted",0.741,33]]}}],"note":"The original draw and \"all 33\" mix two platform builds.","sourceIds":["agent-swebench-c1","agent-swebench-c2","swebench-leaderboard","swebench-protocol"]}}