[{"data":1,"prerenderedAt":381},["ShallowReactive",2],{"results":3},{"baseline":4,"fingerprint":210,"frontier":364},{"AutoBA":5,"BioMaster":53,"Biomni":83,"BixBench-Agent":116,"STELLA":148,"BioMedAgent":178},{"evaluated_tasks":6,"passed_tasks":7,"B1":8,"B2":9,"B3":47,"B4":48,"B5":49,"B6":50,"B7":51,"usage_coverage":52},100,34,0.34,{"by_subject":10,"macro_average":46},{"Basic plot":11,"DNA":15,"Data Operations":17,"Descriptive statistics":20,"FigQA":24,"Fitting & inference":25,"Genetic":28,"Inferential statistics":32,"LitQA":35,"Other":36,"ProtocolQA":37,"RNA":39,"SuppQA":40,"Survival":41,"TableQA":44,"Upset":45},{"passed":12,"evaluated":13,"success_rate":14},3,4,0.75,{"passed":16,"evaluated":13,"success_rate":16},0,{"passed":18,"evaluated":13,"success_rate":19},2,0.5,{"passed":21,"evaluated":22,"success_rate":23},5,17,0.29411764705882354,{"passed":16,"evaluated":18,"success_rate":16},{"passed":13,"evaluated":26,"success_rate":27},6,0.6666666666666666,{"passed":29,"evaluated":30,"success_rate":31},10,32,0.3125,{"passed":12,"evaluated":33,"success_rate":34},9,0.3333333333333333,{"passed":16,"evaluated":18,"success_rate":16},{"passed":18,"evaluated":12,"success_rate":27},{"passed":38,"evaluated":38,"success_rate":38},1,{"passed":16,"evaluated":18,"success_rate":16},{"passed":38,"evaluated":38,"success_rate":38},{"passed":38,"evaluated":42,"success_rate":43},8,0.125,{"passed":16,"evaluated":18,"success_rate":16},{"passed":18,"evaluated":12,"success_rate":27},0.3946844362745098,72381.76,34.41064252519949,27.1,0.24694280000000002,0.7263023529411765,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":21,"B1":54,"B2":55,"B3":77,"B4":78,"B5":79,"B6":80,"B7":81,"usage_coverage":82},0.05,{"by_subject":56,"macro_average":76},{"Basic plot":57,"DNA":58,"Data Operations":59,"Descriptive statistics":61,"FigQA":63,"Fitting & inference":64,"Genetic":66,"Inferential statistics":67,"LitQA":68,"Other":69,"ProtocolQA":70,"RNA":71,"SuppQA":72,"Survival":73,"TableQA":74,"Upset":75},{"passed":16,"evaluated":13,"success_rate":16},{"passed":16,"evaluated":13,"success_rate":16},{"passed":38,"evaluated":13,"success_rate":60},0.25,{"passed":38,"evaluated":22,"success_rate":62},0.058823529411764705,{"passed":16,"evaluated":18,"success_rate":16},{"passed":38,"evaluated":26,"success_rate":65},0.16666666666666666,{"passed":16,"evaluated":30,"success_rate":16},{"passed":16,"evaluated":33,"success_rate":16},{"passed":16,"evaluated":18,"success_rate":16},{"passed":16,"evaluated":12,"success_rate":16},{"passed":38,"evaluated":38,"success_rate":38},{"passed":16,"evaluated":18,"success_rate":16},{"passed":16,"evaluated":38,"success_rate":16},{"passed":16,"evaluated":42,"success_rate":16},{"passed":16,"evaluated":18,"success_rate":16},{"passed":38,"evaluated":12,"success_rate":34},0.1130514705882353,68921.77,14.814270394073798,7.77,0.26699014,5.339802799999999,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":84,"B1":85,"B2":86,"B3":110,"B4":111,"B5":112,"B6":113,"B7":114,"usage_coverage":115},78,0.78,{"by_subject":87,"macro_average":109},{"Basic plot":88,"DNA":89,"Data Operations":90,"Descriptive statistics":91,"FigQA":93,"Fitting & inference":94,"Genetic":95,"Inferential statistics":98,"LitQA":101,"Other":102,"ProtocolQA":103,"RNA":104,"SuppQA":105,"Survival":106,"TableQA":107,"Upset":108},{"passed":13,"evaluated":13,"success_rate":38},{"passed":38,"evaluated":13,"success_rate":60},{"passed":12,"evaluated":13,"success_rate":14},{"passed":29,"evaluated":22,"success_rate":92},0.5882352941176471,{"passed":38,"evaluated":18,"success_rate":19},{"passed":26,"evaluated":26,"success_rate":38},{"passed":96,"evaluated":30,"success_rate":97},28,0.875,{"passed":99,"evaluated":33,"success_rate":100},7,0.7777777777777778,{"passed":18,"evaluated":18,"success_rate":38},{"passed":12,"evaluated":12,"success_rate":38},{"passed":38,"evaluated":38,"success_rate":38},{"passed":38,"evaluated":18,"success_rate":19},{"passed":38,"evaluated":38,"success_rate":38},{"passed":99,"evaluated":42,"success_rate":97},{"passed":16,"evaluated":18,"success_rate":16},{"passed":12,"evaluated":12,"success_rate":38},0.7572508169934641,243650.1,3.7002382298732797,5.62,0.11576269,0.14841370512820512,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":117,"B1":118,"B2":119,"B3":142,"B4":143,"B5":144,"B6":145,"B7":146,"usage_coverage":147},76,0.76,{"by_subject":120,"macro_average":141},{"Basic plot":121,"DNA":122,"Data Operations":123,"Descriptive statistics":124,"FigQA":127,"Fitting & inference":128,"Genetic":129,"Inferential statistics":132,"LitQA":133,"Other":134,"ProtocolQA":135,"RNA":136,"SuppQA":137,"Survival":138,"TableQA":139,"Upset":140},{"passed":13,"evaluated":13,"success_rate":38},{"passed":16,"evaluated":13,"success_rate":16},{"passed":12,"evaluated":13,"success_rate":14},{"passed":125,"evaluated":22,"success_rate":126},11,0.6470588235294118,{"passed":38,"evaluated":18,"success_rate":19},{"passed":26,"evaluated":26,"success_rate":38},{"passed":130,"evaluated":30,"success_rate":131},26,0.8125,{"passed":99,"evaluated":33,"success_rate":100},{"passed":18,"evaluated":18,"success_rate":38},{"passed":12,"evaluated":12,"success_rate":38},{"passed":38,"evaluated":38,"success_rate":38},{"passed":16,"evaluated":18,"success_rate":16},{"passed":38,"evaluated":38,"success_rate":38},{"passed":26,"evaluated":42,"success_rate":14},{"passed":18,"evaluated":18,"success_rate":38},{"passed":12,"evaluated":12,"success_rate":38},0.7648335375816994,40758.82,4.5569090998607376,6.65,0.128044035,0.16847899342105263,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":149,"B1":150,"B2":151,"B3":172,"B4":173,"B5":174,"B6":175,"B7":176,"usage_coverage":177},71,0.71,{"by_subject":152,"macro_average":171},{"Basic plot":153,"DNA":154,"Data Operations":155,"Descriptive statistics":156,"FigQA":157,"Fitting & inference":158,"Genetic":159,"Inferential statistics":162,"LitQA":163,"Other":164,"ProtocolQA":165,"RNA":166,"SuppQA":167,"Survival":168,"TableQA":169,"Upset":170},{"passed":13,"evaluated":13,"success_rate":38},{"passed":16,"evaluated":13,"success_rate":16},{"passed":13,"evaluated":13,"success_rate":38},{"passed":125,"evaluated":22,"success_rate":126},{"passed":38,"evaluated":18,"success_rate":19},{"passed":26,"evaluated":26,"success_rate":38},{"passed":160,"evaluated":30,"success_rate":161},23,0.71875,{"passed":99,"evaluated":33,"success_rate":100},{"passed":18,"evaluated":18,"success_rate":38},{"passed":12,"evaluated":12,"success_rate":38},{"passed":38,"evaluated":38,"success_rate":38},{"passed":38,"evaluated":18,"success_rate":19},{"passed":38,"evaluated":38,"success_rate":38},{"passed":13,"evaluated":42,"success_rate":19},{"passed":38,"evaluated":18,"success_rate":19},{"passed":18,"evaluated":12,"success_rate":27},0.738140829248366,367805.43,6.258834875981323,20.23,0.24669928800000002,0.347463785915493,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":179,"B1":180,"B2":181,"B3":204,"B4":205,"B5":206,"B6":207,"B7":208,"usage_coverage":209},73,0.73,{"by_subject":182,"macro_average":203},{"Basic plot":183,"DNA":184,"Data Operations":185,"Descriptive statistics":186,"FigQA":189,"Fitting & inference":190,"Genetic":192,"Inferential statistics":194,"LitQA":195,"Other":196,"ProtocolQA":197,"RNA":198,"SuppQA":199,"Survival":200,"TableQA":201,"Upset":202},{"passed":13,"evaluated":13,"success_rate":38},{"passed":16,"evaluated":13,"success_rate":16},{"passed":18,"evaluated":13,"success_rate":19},{"passed":187,"evaluated":22,"success_rate":188},12,0.7058823529411765,{"passed":38,"evaluated":18,"success_rate":19},{"passed":21,"evaluated":26,"success_rate":191},0.8333333333333334,{"passed":193,"evaluated":30,"success_rate":14},24,{"passed":26,"evaluated":33,"success_rate":27},{"passed":18,"evaluated":18,"success_rate":38},{"passed":18,"evaluated":12,"success_rate":27},{"passed":16,"evaluated":38,"success_rate":16},{"passed":18,"evaluated":18,"success_rate":38},{"passed":38,"evaluated":38,"success_rate":38},{"passed":99,"evaluated":42,"success_rate":97},{"passed":18,"evaluated":18,"success_rate":38},{"passed":12,"evaluated":12,"success_rate":38},0.7185968137254902,167571.99,10.369415263613066,13.21,0.41211416,0.5645399452054795,{"tokens":6,"elapsed_seconds":6,"model_requests":6,"cost_usd":6},{"AutoBA":211,"BioMaster":248,"Biomni":262,"BixBench-Agent":285,"STELLA":315,"BioMedAgent":342},{"evaluated_tasks":6,"passed_tasks":212,"success_rate":213,"subdimensions":214,"dimensions":222,"weighted_pass":227,"total_load":231,"B3":244,"B4":244,"B5":244,"B6":245,"B7":246,"usage_coverage":247},33,0.33,{"P1":215,"P2":216,"A1":217,"A2":218,"R1":219,"R2":43,"E1":220,"E2":221},0.13333333333333333,0.21518987341772153,0.352112676056338,0.4,0.44,0.1206896551724138,0.24324324324324326,{"P":223,"A":224,"R":225,"E":226},0.2073170731707317,0.3708609271523179,0.3170731707317073,0.15714285714285714,{"P1":26,"P2":22,"A1":228,"A2":228,"R1":125,"R2":18,"E1":99,"E2":33,"P":22,"A":229,"R":230,"E":125},50,56,13,{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},45,79,142,125,25,16,58,37,82,151,41,70,null,0.568865379,1.7238344818181819,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":13,"success_rate":249,"subdimensions":250,"dimensions":254,"weighted_pass":257,"total_load":258,"B3":244,"B4":244,"B5":244,"B6":259,"B7":260,"usage_coverage":261},0.04,{"P1":16,"P2":16,"A1":251,"A2":252,"R1":253,"R2":16,"E1":16,"E2":16},0.028169014084507043,0.024,0.2,{"P":16,"A":255,"R":256,"E":16},0.026490066225165563,0.12195121951219512,{"P1":16,"P2":16,"A1":13,"A2":12,"R1":21,"R2":16,"E1":16,"E2":16,"P":16,"A":13,"R":21,"E":16},{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},0.2715634,6.789085,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":263,"success_rate":14,"subdimensions":264,"dimensions":272,"weighted_pass":276,"total_load":281,"B3":244,"B4":244,"B5":244,"B6":282,"B7":283,"usage_coverage":284},75,{"P1":265,"P2":266,"A1":267,"A2":268,"R1":269,"R2":14,"E1":270,"E2":271},0.6444444444444445,0.7088607594936709,0.7887323943661971,0.8,0.68,0.7068965517241379,0.7567567567567568,{"P":273,"A":274,"R":273,"E":275},0.7073170731707317,0.7814569536423841,0.7,{"P1":277,"P2":229,"A1":278,"A2":6,"R1":22,"R2":187,"E1":242,"E2":96,"P":238,"A":279,"R":277,"E":280},29,112,118,49,{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},0.10546000900000001,0.14061334533333333,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":286,"success_rate":287,"subdimensions":288,"dimensions":296,"weighted_pass":301,"total_load":311,"B3":244,"B4":244,"B5":244,"B6":312,"B7":313,"usage_coverage":314},86,0.86,{"P1":289,"P2":290,"A1":291,"A2":292,"R1":293,"R2":14,"E1":294,"E2":295},0.8444444444444444,0.8860759493670886,0.8873239436619719,0.904,0.6,0.7586206896551724,0.918918918918919,{"P":297,"A":298,"R":299,"E":300},0.8780487804878049,0.8940397350993378,0.6585365853658537,0.7857142857142857,{"P1":302,"P2":243,"A1":303,"A2":304,"R1":305,"R2":187,"E1":306,"E2":7,"P":307,"A":308,"R":309,"E":310},38,126,113,15,44,72,135,27,55,{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},0.12239185,0.1423161046511628,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":263,"success_rate":14,"subdimensions":316,"dimensions":324,"weighted_pass":328,"total_load":338,"B3":244,"B4":244,"B5":244,"B6":339,"B7":340,"usage_coverage":341},{"P1":317,"P2":318,"A1":319,"A2":320,"R1":118,"R2":321,"E1":322,"E2":323},0.7555555555555555,0.7721518987341772,0.8028169014084507,0.824,0.1875,0.6206896551724138,0.6486486486486487,{"P":325,"A":326,"R":327,"E":293},0.7804878048780488,0.8079470198675497,0.5365853658536586,{"P1":7,"P2":329,"A1":330,"A2":331,"R1":332,"R2":12,"E1":333,"E2":193,"P":334,"A":335,"R":336,"E":337},61,114,103,19,36,64,122,22,42,{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},0.30202687,0.40270249333333336,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"evaluated_tasks":6,"passed_tasks":343,"success_rate":344,"subdimensions":345,"dimensions":352,"weighted_pass":355,"total_load":360,"B3":244,"B4":244,"B5":244,"B6":361,"B7":362,"usage_coverage":363},81,0.81,{"P1":346,"P2":347,"A1":348,"A2":349,"R1":268,"R2":14,"E1":350,"E2":351},0.8222222222222222,0.8987341772151899,0.8309859154929577,0.856,0.6551724137931034,0.8378378378378378,{"P":297,"A":353,"R":325,"E":354},0.8344370860927153,0.6857142857142857,{"P1":239,"P2":149,"A1":279,"A2":356,"R1":357,"R2":187,"E1":302,"E2":358,"P":307,"A":303,"R":30,"E":359},107,20,31,48,{"P1":232,"P2":233,"A1":234,"A2":235,"R1":236,"R2":237,"E1":238,"E2":239,"P":240,"A":241,"R":242,"E":243},1.1674467129999997,1.4412922382716047,{"tokens":16,"elapsed_seconds":16,"model_requests":16,"cost_usd":6},{"AutoBA":365,"BioMaster":367,"Biomni":369,"BixBench-Agent":372,"STELLA":375,"BioMedAgent":378},{"evaluated_cases":21,"F1":366,"F2":16,"F3":16},0.375,{"evaluated_cases":21,"F1":218,"F2":368,"F3":16},0.015384615384615385,{"evaluated_cases":21,"F1":268,"F2":370,"F3":371},0.08954116059379218,0.06666666666666667,{"evaluated_cases":21,"F1":373,"F2":374,"F3":371},0.65,0.10695970695970695,{"evaluated_cases":21,"F1":376,"F2":377,"F3":371},0.725,0.19862637362637364,{"evaluated_cases":21,"F1":379,"F2":380,"F3":215},0.85,0.1990649701176017,1791659693480]