{"i":0,"slug":"swe-bench-verified","chart":{"id":"swebench-by-difficulty-band","title":"Resolved rate by difficulty band","subtitle":"Band = how many of the 11 public panel models solved the instance","kind":"grouped-bar","unit":"rate","xLabel":"Difficulty band","yLabel":"Resolved","series":[{"name":"Agent","points":{"$k":["label","value","lo","hi","n","highlight"],"$r":[["No panel model solved it",0.25,0.0456,0.6994,4,true],["Under half solved it",0.75,0.3006,0.9544,4,true],["Half or more solved it",0.8182,0.523,0.9486,11,true],["Every panel model solved it",0.8571,0.6006,0.9599,14,true]]}},{"name":"Public panel mean","points":{"$k":["label","value","n"],"$r":[["No panel model solved it",0,4],["Under half solved it",0.2727,4],["Half or more solved it",0.8512,11],["Every panel model solved it",1,14]]}}],"note":"Agent whiskers are 95% Wilson intervals. The \"no panel model solved it\" band has 4 instances; Agent resolved 1 (matplotlib__matplotlib-21568).","sourceIds":["agent-swebench-c1","agent-swebench-c2","swebench-leaderboard","swebench-protocol"]}}