{"i":0,"slug":"swe-bench-verified","chart":{"id":"swebench-model-calls","title":"Model calls per instance","subtitle":"Mean over the same 33 instances","kind":"bar","unit":"calls","yLabel":"Calls per instance","series":[{"name":"Mean calls","points":{"$k":["label","value","n","highlight"],"$r":[["DeepSeek V3.2 (high)",88.2,33,"\u0001"],["GLM 5 (high)",77.5,33,"\u0001"],["Claude 4.5 Haiku (high)",68.5,33,"\u0001"],["MiniMax M2.5 (high)",58.4,33,"\u0001"],["Kimi K2.5 (high)",56.7,33,"\u0001"],["Gemini 3 Flash (high)",54.2,33,"\u0001"],["Claude 4.5 Sonnet (high)",51,33,"\u0001"],["Agent",49.5,33,true],["Claude 4.5 Opus (high)",35.9,33,"\u0001"],["GPT 5.2 (high)",35.6,33,"\u0001"],["Claude 4.6 Opus",28.9,33,"\u0001"],["GPT 5 mini",20.8,33,"\u0001"]]}}],"note":"A panel call is one bash-agent step. An Agent call is one model request of any stage (research, plan, act, verify, review).","sourceIds":["agent-swebench-c1","agent-swebench-c2","swebench-leaderboard"]}}