[{"id":"swebench-per-instance","title":"Every attempt","columns":{"$k":["key","label","unit"],"$r":[["instance","Instance","text"],["band","Panel solved","text"],["outcome","Agent outcome","text"],["minutes","Minutes","minutes"],["calls","Calls","calls"],["costUsd","Cost (notional)","usd"],["campaign","Campaign","text"]]},"rows":{"$k":["instance","band","outcome","minutes","calls","costUsd","campaign"],"$r":[["astropy__astropy-13579","11/11","resolved",54.1,65,4,"2"],["astropy__astropy-14096","10/11","resolved",10.4,64,3.35,"2"],["astropy__astropy-7336","11/11","unresolved",23,48,2.03,"2"],["django__django-10554","0/11","unresolved",4.7,34,1.52,"1"],["django__django-11333","11/11","resolved",8,46,2.51,"1"],["django__django-11885","3/11","resolved",7.3,38,2.27,"1"],["django__django-12193","10/11","resolved",5.7,43,2.06,"1"],["django__django-12741","11/11","resolved",10.5,54,2.98,"1"],["django__django-13158","10/11","resolved",7,43,2.15,"1"],["django__django-13925","8/11","resolved",6.8,43,2.29,"1"],["django__django-14034","0/11","unresolved",11.5,54,3.03,"1"],["django__django-14373","11/11","resolved",5.7,38,1.74,"1"],["django__django-14559","11/11","resolved",7.2,47,2.71,"1"],["django__django-14631","9/11","empty patch",38.2,47,2.8,"1"],["django__django-14672","11/11","resolved",9.1,58,2.99,"1"],["django__django-15022","4/11","unresolved",15,62,4.1,"1"],["django__django-15280","7/11","resolved",11,59,3.67,"1"],["django__django-15572","10/11","resolved",5.3,42,1.81,"1"],["django__django-15732","3/11","resolved",10.9,59,2.9,"1"],["django__django-16255","10/11","resolved",7.6,47,2.55,"1"],["django__django-16333","11/11","resolved",13,37,1.61,"1"],["django__django-17029","11/11","resolved",7.8,42,2.28,"1"],["matplotlib__matplotlib-21568","0/11","resolved",9.4,53,3.02,"2"],["matplotlib__matplotlib-24149","10/11","resolved",41.1,64,3.64,"2"],["matplotlib__matplotlib-24970","11/11","resolved",33,66,3.9,"2"],["pydata__xarray-6721","11/11","resolved",16.2,57,4.09,"1"],["scikit-learn__scikit-learn-14894","11/11","resolved",35.2,50,3.23,"2"],["scikit-learn__scikit-learn-25973","10/11","resolved",8.6,44,2.43,"2"],["sphinx-doc__sphinx-10435","2/11","resolved",16.8,67,4.83,"1"],["sphinx-doc__sphinx-9698","11/11","resolved",9.6,49,2.69,"1"],["sympy__sympy-18189","11/11","empty patch",1.6,13,0.89,"1"],["sympy__sympy-20428","0/11","unresolved",21,71,4.81,"1"],["sympy__sympy-22456","9/11","empty patch",6.4,28,1.75,"1"]]}},{"id":"swebench-panel","title":"Public panel on the same instances","columns":{"$k":["key","label","unit"],"$r":[["system","System","text"],["resolved","Resolved of 33","count"],["rate","Rate","rate"],["board500","Full Verified board (500)","percent"],["meanCost","Mean cost per instance, these 33","usd"]]},"rows":{"$k":["system","resolved","rate","board500","meanCost"],"$r":[["GPT 5.2 (high)",28,0.8485,72.8,0.533],["Gemini 3 Flash (high)",27,0.8182,75.8,0.357],["GLM 5 (high)",26,0.7879,72.8,0.525],["Agent (Sonnet 5.5, full pipeline)",25,0.7576,null,2.81],["Claude 4.5 Sonnet (high)",25,0.7576,71.4,0.692],["Claude 4.5 Haiku (high)",25,0.7576,66.6,0.363],["Claude 4.5 Opus (high)",24,0.7273,76.8,0.861],["DeepSeek V3.2 (high)",24,0.7273,70,0.463],["MiniMax M2.5 (high)",23,0.697,75.8,0.075],["Claude 4.6 Opus",23,0.697,75.6,0.61],["Kimi K2.5 (high)",23,0.697,70.8,0.179],["GPT 5 mini",21,0.6364,56.2,0.051]]}}]