Davidmg0815's picture
Upload folder using huggingface_hub
0794b44 verified
Raw
History Blame
30 kB
{
"modell": "Qwen3.6-27B Q5_K_M",
"satz": "humanevalplus",
"reasoning": false,
"n": 164,
"bestanden": 145,
"quote": 88.4,
"tps_median": 31.3,
"tokens_gesamt": 38535,
"tokens_je_aufgabe": 235.0,
"am_limit": 1,
"dauer_s": 1393.9,
"aufgaben": [
{
"task": "HumanEval/0",
"ok": true,
"grund": "",
"tps": 31.290492248277936,
"tokens": 173,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.03
},
{
"task": "HumanEval/1",
"ok": true,
"grund": "",
"tps": 31.20052427733142,
"tokens": 230,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.88
},
{
"task": "HumanEval/2",
"ok": true,
"grund": "",
"tps": 31.400670614734487,
"tokens": 97,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.58
},
{
"task": "HumanEval/3",
"ok": true,
"grund": "",
"tps": 31.403096345299648,
"tokens": 157,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.48
},
{
"task": "HumanEval/4",
"ok": true,
"grund": "",
"tps": 31.35233569335412,
"tokens": 169,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.87
},
{
"task": "HumanEval/5",
"ok": true,
"grund": "",
"tps": 31.183242044729727,
"tokens": 154,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.42
},
{
"task": "HumanEval/6",
"ok": true,
"grund": "",
"tps": 31.290982596803556,
"tokens": 214,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.33
},
{
"task": "HumanEval/7",
"ok": true,
"grund": "",
"tps": 31.46563264604338,
"tokens": 112,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.05
},
{
"task": "HumanEval/8",
"ok": true,
"grund": "",
"tps": 31.37087650998806,
"tokens": 163,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.67
},
{
"task": "HumanEval/9",
"ok": true,
"grund": "",
"tps": 31.337708103176887,
"tokens": 162,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.66
},
{
"task": "HumanEval/10",
"ok": true,
"grund": "",
"tps": 31.302047099724533,
"tokens": 289,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.75
},
{
"task": "HumanEval/11",
"ok": true,
"grund": "",
"tps": 31.401877054148233,
"tokens": 113,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.05
},
{
"task": "HumanEval/12",
"ok": true,
"grund": "",
"tps": 31.36262520854308,
"tokens": 128,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.57
},
{
"task": "HumanEval/13",
"ok": true,
"grund": "",
"tps": 31.48357057822078,
"tokens": 107,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.89
},
{
"task": "HumanEval/14",
"ok": true,
"grund": "",
"tps": 31.577281251344502,
"tokens": 80,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.96
},
{
"task": "HumanEval/15",
"ok": true,
"grund": "",
"tps": 31.512752560154247,
"tokens": 92,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.35
},
{
"task": "HumanEval/16",
"ok": true,
"grund": "",
"tps": 31.594603017713652,
"tokens": 81,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.01
},
{
"task": "HumanEval/17",
"ok": true,
"grund": "",
"tps": 31.261929090997725,
"tokens": 261,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.9
},
{
"task": "HumanEval/18",
"ok": true,
"grund": "",
"tps": 31.30549555335574,
"tokens": 161,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.65
},
{
"task": "HumanEval/19",
"ok": true,
"grund": "",
"tps": 31.24467348173114,
"tokens": 246,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.38
},
{
"task": "HumanEval/20",
"ok": true,
"grund": "",
"tps": 31.25658846032969,
"tokens": 310,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.47
},
{
"task": "HumanEval/21",
"ok": true,
"grund": "",
"tps": 31.327685151894634,
"tokens": 193,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.69
},
{
"task": "HumanEval/22",
"ok": true,
"grund": "",
"tps": 31.467670670464997,
"tokens": 119,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.28
},
{
"task": "HumanEval/23",
"ok": true,
"grund": "",
"tps": 31.75272654072617,
"tokens": 53,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.09
},
{
"task": "HumanEval/24",
"ok": true,
"grund": "",
"tps": 31.559355073569996,
"tokens": 86,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.15
},
{
"task": "HumanEval/25",
"ok": false,
"grund": "Zeitueberschreitung (25s)",
"tps": 31.280268717739308,
"tokens": 201,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.95
},
{
"task": "HumanEval/26",
"ok": true,
"grund": "",
"tps": 31.269660799227513,
"tokens": 150,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.31
},
{
"task": "HumanEval/27",
"ok": true,
"grund": "",
"tps": 31.56328602105598,
"tokens": 58,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.32
},
{
"task": "HumanEval/28",
"ok": true,
"grund": "",
"tps": 31.442444605150275,
"tokens": 70,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.69
},
{
"task": "HumanEval/29",
"ok": true,
"grund": "",
"tps": 31.522637672910506,
"tokens": 107,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.91
},
{
"task": "HumanEval/30",
"ok": true,
"grund": "",
"tps": 31.415105874557,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.99
},
{
"task": "HumanEval/31",
"ok": true,
"grund": "",
"tps": 31.250820700837068,
"tokens": 213,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.35
},
{
"task": "HumanEval/32",
"ok": false,
"grund": "TypeError: Value after * must be an iterable, not float",
"tps": 31.16851681379837,
"tokens": 752,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 24.82
},
{
"task": "HumanEval/33",
"ok": true,
"grund": "",
"tps": 31.29224809085994,
"tokens": 275,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.38
},
{
"task": "HumanEval/34",
"ok": true,
"grund": "",
"tps": 31.51850734145738,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.24
},
{
"task": "HumanEval/35",
"ok": true,
"grund": "",
"tps": 31.480250037565348,
"tokens": 97,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.56
},
{
"task": "HumanEval/36",
"ok": true,
"grund": "",
"tps": 31.38906100066116,
"tokens": 142,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.0
},
{
"task": "HumanEval/37",
"ok": true,
"grund": "",
"tps": 31.34561004731287,
"tokens": 198,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.86
},
{
"task": "HumanEval/38",
"ok": true,
"grund": "",
"tps": 31.157634345926457,
"tokens": 277,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.47
},
{
"task": "HumanEval/39",
"ok": true,
"grund": "",
"tps": 31.281273636606908,
"tokens": 256,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.71
},
{
"task": "HumanEval/40",
"ok": true,
"grund": "",
"tps": 31.222919213679617,
"tokens": 314,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.64
},
{
"task": "HumanEval/41",
"ok": true,
"grund": "",
"tps": 31.272677400856196,
"tokens": 166,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.89
},
{
"task": "HumanEval/42",
"ok": true,
"grund": "",
"tps": 31.310768389976573,
"tokens": 132,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.74
},
{
"task": "HumanEval/43",
"ok": true,
"grund": "",
"tps": 31.301180739713864,
"tokens": 201,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.0
},
{
"task": "HumanEval/44",
"ok": true,
"grund": "",
"tps": 31.249147076286288,
"tokens": 158,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.58
},
{
"task": "HumanEval/45",
"ok": true,
"grund": "",
"tps": 31.655303292098786,
"tokens": 60,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.34
},
{
"task": "HumanEval/46",
"ok": true,
"grund": "",
"tps": 31.241408612631528,
"tokens": 300,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.18
},
{
"task": "HumanEval/47",
"ok": true,
"grund": "",
"tps": 31.359869146819687,
"tokens": 152,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.34
},
{
"task": "HumanEval/48",
"ok": true,
"grund": "",
"tps": 31.539703048257923,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.24
},
{
"task": "HumanEval/49",
"ok": true,
"grund": "",
"tps": 31.383305861230518,
"tokens": 134,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.8
},
{
"task": "HumanEval/50",
"ok": true,
"grund": "",
"tps": 31.31762428740631,
"tokens": 133,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.77
},
{
"task": "HumanEval/51",
"ok": true,
"grund": "",
"tps": 31.351619624669805,
"tokens": 165,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.81
},
{
"task": "HumanEval/52",
"ok": true,
"grund": "",
"tps": 31.45259402123931,
"tokens": 100,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.66
},
{
"task": "HumanEval/53",
"ok": true,
"grund": "",
"tps": 31.580579283522788,
"tokens": 66,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.55
},
{
"task": "HumanEval/54",
"ok": true,
"grund": "",
"tps": 31.29288802063542,
"tokens": 161,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.7
},
{
"task": "HumanEval/55",
"ok": false,
"grund": "ValueError: n must be a positive integer",
"tps": 31.349694219905604,
"tokens": 143,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.02
},
{
"task": "HumanEval/56",
"ok": true,
"grund": "",
"tps": 31.23659512358948,
"tokens": 157,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.55
},
{
"task": "HumanEval/57",
"ok": true,
"grund": "",
"tps": 31.285580149817623,
"tokens": 163,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.74
},
{
"task": "HumanEval/58",
"ok": true,
"grund": "",
"tps": 31.376335002715262,
"tokens": 143,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.11
},
{
"task": "HumanEval/59",
"ok": true,
"grund": "",
"tps": 31.32082177397564,
"tokens": 193,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.63
},
{
"task": "HumanEval/60",
"ok": true,
"grund": "",
"tps": 31.39409891401533,
"tokens": 125,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.51
},
{
"task": "HumanEval/61",
"ok": true,
"grund": "",
"tps": 31.275229436887493,
"tokens": 156,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.5
},
{
"task": "HumanEval/62",
"ok": true,
"grund": "",
"tps": 31.348217885161446,
"tokens": 150,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.31
},
{
"task": "HumanEval/63",
"ok": true,
"grund": "",
"tps": 31.222155241359268,
"tokens": 247,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.48
},
{
"task": "HumanEval/64",
"ok": true,
"grund": "",
"tps": 31.248992952375556,
"tokens": 192,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.7
},
{
"task": "HumanEval/65",
"ok": true,
"grund": "",
"tps": 31.364592964963066,
"tokens": 152,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.37
},
{
"task": "HumanEval/66",
"ok": true,
"grund": "",
"tps": 31.302438571759165,
"tokens": 140,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.02
},
{
"task": "HumanEval/67",
"ok": true,
"grund": "",
"tps": 31.26965490371993,
"tokens": 272,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.35
},
{
"task": "HumanEval/68",
"ok": true,
"grund": "",
"tps": 31.178093704488795,
"tokens": 429,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.52
},
{
"task": "HumanEval/69",
"ok": true,
"grund": "",
"tps": 31.231637593605083,
"tokens": 226,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.83
},
{
"task": "HumanEval/70",
"ok": true,
"grund": "",
"tps": 31.319606007285444,
"tokens": 237,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.12
},
{
"task": "HumanEval/71",
"ok": true,
"grund": "",
"tps": 31.335235040626582,
"tokens": 208,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.19
},
{
"task": "HumanEval/72",
"ok": true,
"grund": "",
"tps": 31.18725475963371,
"tokens": 255,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.84
},
{
"task": "HumanEval/73",
"ok": true,
"grund": "",
"tps": 31.273799733904635,
"tokens": 210,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.3
},
{
"task": "HumanEval/74",
"ok": true,
"grund": "",
"tps": 31.300102324436075,
"tokens": 256,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.79
},
{
"task": "HumanEval/75",
"ok": true,
"grund": "",
"tps": 31.31544678929939,
"tokens": 204,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.01
},
{
"task": "HumanEval/76",
"ok": false,
"grund": "ValueError: math domain error",
"tps": 31.20177194334023,
"tokens": 472,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.69
},
{
"task": "HumanEval/77",
"ok": true,
"grund": "",
"tps": 31.288177680677922,
"tokens": 173,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.07
},
{
"task": "HumanEval/78",
"ok": true,
"grund": "",
"tps": 31.187682119759025,
"tokens": 373,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.71
},
{
"task": "HumanEval/79",
"ok": true,
"grund": "",
"tps": 31.25835212996076,
"tokens": 169,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.97
},
{
"task": "HumanEval/80",
"ok": true,
"grund": "",
"tps": 31.29469374270664,
"tokens": 194,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.74
},
{
"task": "HumanEval/81",
"ok": true,
"grund": "",
"tps": 31.198340625013433,
"tokens": 530,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 17.69
},
{
"task": "HumanEval/82",
"ok": true,
"grund": "",
"tps": 31.338852127738964,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.92
},
{
"task": "HumanEval/83",
"ok": false,
"grund": "AssertionError",
"tps": 31.431526419694695,
"tokens": 105,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.78
},
{
"task": "HumanEval/84",
"ok": true,
"grund": "",
"tps": 31.360895611425963,
"tokens": 180,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.3
},
{
"task": "HumanEval/85",
"ok": true,
"grund": "",
"tps": 31.450167210055668,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.22
},
{
"task": "HumanEval/86",
"ok": true,
"grund": "",
"tps": 31.254299589447598,
"tokens": 184,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.43
},
{
"task": "HumanEval/87",
"ok": true,
"grund": "",
"tps": 31.270696580606266,
"tokens": 357,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.12
},
{
"task": "HumanEval/88",
"ok": true,
"grund": "",
"tps": 31.266838206932604,
"tokens": 339,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.45
},
{
"task": "HumanEval/89",
"ok": true,
"grund": "",
"tps": 31.3318031657402,
"tokens": 199,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.88
},
{
"task": "HumanEval/90",
"ok": true,
"grund": "",
"tps": 31.249137015111504,
"tokens": 172,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.06
},
{
"task": "HumanEval/91",
"ok": false,
"grund": "AssertionError",
"tps": 31.21374993110773,
"tokens": 239,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.18
},
{
"task": "HumanEval/92",
"ok": true,
"grund": "",
"tps": 31.292708160371937,
"tokens": 196,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.81
},
{
"task": "HumanEval/93",
"ok": false,
"grund": "AssertionError",
"tps": 31.267595452954517,
"tokens": 263,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.93
},
{
"task": "HumanEval/94",
"ok": true,
"grund": "",
"tps": 31.1422628581702,
"tokens": 467,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.74
},
{
"task": "HumanEval/95",
"ok": true,
"grund": "",
"tps": 31.220978495925554,
"tokens": 287,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.79
},
{
"task": "HumanEval/96",
"ok": true,
"grund": "",
"tps": 31.280723229871526,
"tokens": 256,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.77
},
{
"task": "HumanEval/97",
"ok": false,
"grund": "AssertionError",
"tps": 31.337177661056185,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.97
},
{
"task": "HumanEval/98",
"ok": true,
"grund": "",
"tps": 31.412054101529243,
"tokens": 126,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.48
},
{
"task": "HumanEval/99",
"ok": true,
"grund": "",
"tps": 31.207260836348627,
"tokens": 314,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.65
},
{
"task": "HumanEval/100",
"ok": true,
"grund": "",
"tps": 31.273534124164144,
"tokens": 198,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.89
},
{
"task": "HumanEval/101",
"ok": false,
"grund": "AssertionError",
"tps": 31.370460310725537,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.96
},
{
"task": "HumanEval/102",
"ok": true,
"grund": "",
"tps": 31.224446464033477,
"tokens": 170,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.97
},
{
"task": "HumanEval/103",
"ok": true,
"grund": "",
"tps": 31.26813040556091,
"tokens": 283,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.63
},
{
"task": "HumanEval/104",
"ok": true,
"grund": "",
"tps": 31.28333895024275,
"tokens": 185,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.45
},
{
"task": "HumanEval/105",
"ok": true,
"grund": "",
"tps": 31.193472381049737,
"tokens": 462,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.52
},
{
"task": "HumanEval/106",
"ok": true,
"grund": "",
"tps": 31.2306441550543,
"tokens": 251,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.6
},
{
"task": "HumanEval/107",
"ok": true,
"grund": "",
"tps": 31.287522833413426,
"tokens": 326,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.08
},
{
"task": "HumanEval/108",
"ok": true,
"grund": "",
"tps": 31.24378466238417,
"tokens": 298,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.1
},
{
"task": "HumanEval/109",
"ok": true,
"grund": "",
"tps": 31.201498982563052,
"tokens": 419,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.17
},
{
"task": "HumanEval/110",
"ok": true,
"grund": "",
"tps": 31.23521179730478,
"tokens": 346,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.7
},
{
"task": "HumanEval/111",
"ok": true,
"grund": "",
"tps": 31.306498446415013,
"tokens": 256,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.76
},
{
"task": "HumanEval/112",
"ok": true,
"grund": "",
"tps": 31.279275649849666,
"tokens": 241,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.28
},
{
"task": "HumanEval/113",
"ok": true,
"grund": "",
"tps": 31.296989772852353,
"tokens": 265,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.11
},
{
"task": "HumanEval/114",
"ok": true,
"grund": "",
"tps": 31.296639681606443,
"tokens": 173,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.98
},
{
"task": "HumanEval/115",
"ok": true,
"grund": "",
"tps": 31.155898952200094,
"tokens": 392,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.32
},
{
"task": "HumanEval/116",
"ok": true,
"grund": "",
"tps": 31.276646360014418,
"tokens": 198,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.93
},
{
"task": "HumanEval/117",
"ok": true,
"grund": "",
"tps": 31.31612581299599,
"tokens": 272,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.33
},
{
"task": "HumanEval/118",
"ok": true,
"grund": "",
"tps": 31.210612340767693,
"tokens": 409,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.7
},
{
"task": "HumanEval/119",
"ok": true,
"grund": "",
"tps": 31.21114360097014,
"tokens": 291,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.91
},
{
"task": "HumanEval/120",
"ok": true,
"grund": "",
"tps": 31.297519353725786,
"tokens": 256,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.85
},
{
"task": "HumanEval/121",
"ok": true,
"grund": "",
"tps": 31.374962408146892,
"tokens": 135,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.83
},
{
"task": "HumanEval/122",
"ok": true,
"grund": "",
"tps": 31.283926274410504,
"tokens": 212,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.3
},
{
"task": "HumanEval/123",
"ok": true,
"grund": "",
"tps": 31.260748897552066,
"tokens": 324,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.03
},
{
"task": "HumanEval/124",
"ok": true,
"grund": "",
"tps": 31.195049756856655,
"tokens": 622,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 20.68
},
{
"task": "HumanEval/125",
"ok": true,
"grund": "",
"tps": 31.32241132451341,
"tokens": 225,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.75
},
{
"task": "HumanEval/126",
"ok": true,
"grund": "",
"tps": 31.201563205234883,
"tokens": 451,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.16
},
{
"task": "HumanEval/127",
"ok": false,
"grund": "AssertionError",
"tps": 31.172315544093063,
"tokens": 435,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.66
},
{
"task": "HumanEval/128",
"ok": true,
"grund": "",
"tps": 31.29177262102231,
"tokens": 227,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.8
},
{
"task": "HumanEval/129",
"ok": false,
"grund": "SyntaxError: invalid syntax",
"tps": 31.054015198766663,
"tokens": 1200,
"denk_zeichen": 0,
"abbruch": "length",
"sekunden": 39.46
},
{
"task": "HumanEval/130",
"ok": false,
"grund": "RecursionError: maximum recursion depth exceeded",
"tps": 31.125189088899546,
"tokens": 922,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 30.32
},
{
"task": "HumanEval/131",
"ok": true,
"grund": "",
"tps": 31.360578707212408,
"tokens": 144,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.09
},
{
"task": "HumanEval/132",
"ok": false,
"grund": "AssertionError",
"tps": 31.3207043996011,
"tokens": 206,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.12
},
{
"task": "HumanEval/133",
"ok": true,
"grund": "",
"tps": 31.346634472825855,
"tokens": 185,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.48
},
{
"task": "HumanEval/134",
"ok": false,
"grund": "AssertionError",
"tps": 31.18310377614204,
"tokens": 686,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 22.55
},
{
"task": "HumanEval/135",
"ok": true,
"grund": "",
"tps": 31.327721396055775,
"tokens": 149,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.3
},
{
"task": "HumanEval/136",
"ok": true,
"grund": "",
"tps": 31.315037510416293,
"tokens": 213,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.37
},
{
"task": "HumanEval/137",
"ok": true,
"grund": "",
"tps": 31.313341771877486,
"tokens": 234,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.03
},
{
"task": "HumanEval/138",
"ok": true,
"grund": "",
"tps": 31.260716622914146,
"tokens": 334,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.16
},
{
"task": "HumanEval/139",
"ok": true,
"grund": "",
"tps": 31.248651137360977,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.98
},
{
"task": "HumanEval/140",
"ok": true,
"grund": "",
"tps": 31.32326648835048,
"tokens": 166,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.84
},
{
"task": "HumanEval/141",
"ok": true,
"grund": "",
"tps": 31.25296078185805,
"tokens": 412,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.84
},
{
"task": "HumanEval/142",
"ok": true,
"grund": "",
"tps": 31.287655181881007,
"tokens": 240,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.26
},
{
"task": "HumanEval/143",
"ok": true,
"grund": "",
"tps": 31.295776818376364,
"tokens": 290,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.84
},
{
"task": "HumanEval/144",
"ok": true,
"grund": "",
"tps": 31.341109584973186,
"tokens": 200,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.96
},
{
"task": "HumanEval/145",
"ok": false,
"grund": "AssertionError",
"tps": 31.299961377744626,
"tokens": 165,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.82
},
{
"task": "HumanEval/146",
"ok": true,
"grund": "",
"tps": 31.29006733711048,
"tokens": 212,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.32
},
{
"task": "HumanEval/147",
"ok": true,
"grund": "",
"tps": 31.162579850902198,
"tokens": 607,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 20.06
},
{
"task": "HumanEval/148",
"ok": true,
"grund": "",
"tps": 31.2739397077887,
"tokens": 333,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.27
},
{
"task": "HumanEval/149",
"ok": true,
"grund": "",
"tps": 31.304694951046987,
"tokens": 266,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.1
},
{
"task": "HumanEval/150",
"ok": true,
"grund": "",
"tps": 31.367030005086725,
"tokens": 143,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.08
},
{
"task": "HumanEval/151",
"ok": false,
"grund": "AssertionError",
"tps": 31.30848986121439,
"tokens": 197,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.85
},
{
"task": "HumanEval/152",
"ok": true,
"grund": "",
"tps": 31.3034742505356,
"tokens": 259,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.94
},
{
"task": "HumanEval/153",
"ok": true,
"grund": "",
"tps": 31.213405442693713,
"tokens": 358,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.18
},
{
"task": "HumanEval/154",
"ok": false,
"grund": "AssertionError",
"tps": 31.226822628851036,
"tokens": 201,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.99
},
{
"task": "HumanEval/155",
"ok": true,
"grund": "",
"tps": 31.360862407633714,
"tokens": 156,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.45
},
{
"task": "HumanEval/156",
"ok": true,
"grund": "",
"tps": 31.213381311376814,
"tokens": 301,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.17
},
{
"task": "HumanEval/157",
"ok": true,
"grund": "",
"tps": 31.2903996113403,
"tokens": 152,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.36
},
{
"task": "HumanEval/158",
"ok": true,
"grund": "",
"tps": 31.227411195026914,
"tokens": 386,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.91
},
{
"task": "HumanEval/159",
"ok": true,
"grund": "",
"tps": 31.200973982779626,
"tokens": 341,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.67
},
{
"task": "HumanEval/160",
"ok": false,
"grund": "AssertionError",
"tps": 31.22767783803315,
"tokens": 326,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.06
},
{
"task": "HumanEval/161",
"ok": true,
"grund": "",
"tps": 31.291577461224357,
"tokens": 160,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.65
},
{
"task": "HumanEval/162",
"ok": true,
"grund": "",
"tps": 31.339654037236375,
"tokens": 116,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.18
},
{
"task": "HumanEval/163",
"ok": false,
"grund": "AssertionError",
"tps": 31.248359961877,
"tokens": 156,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.51
}
]
}