Davidmg0815's picture
Upload folder using huggingface_hub
0794b44 verified
Raw
History Blame
29.9 kB
{
"modell": "Qwen3.8-27B Q8_0",
"satz": "humanevalplus",
"reasoning": false,
"n": 164,
"bestanden": 145,
"quote": 88.4,
"tps_median": 19.5,
"tokens_gesamt": 26404,
"tokens_je_aufgabe": 161.0,
"am_limit": 1,
"dauer_s": 1535.6,
"aufgaben": [
{
"task": "HumanEval/0",
"ok": true,
"grund": "",
"tps": 19.204284201458425,
"tokens": 168,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.09
},
{
"task": "HumanEval/1",
"ok": true,
"grund": "",
"tps": 19.468605776362754,
"tokens": 213,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.6
},
{
"task": "HumanEval/2",
"ok": true,
"grund": "",
"tps": 19.333778990949057,
"tokens": 92,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.2
},
{
"task": "HumanEval/3",
"ok": true,
"grund": "",
"tps": 19.841793029734752,
"tokens": 152,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.23
},
{
"task": "HumanEval/4",
"ok": true,
"grund": "",
"tps": 19.386878157017165,
"tokens": 164,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.94
},
{
"task": "HumanEval/5",
"ok": true,
"grund": "",
"tps": 19.484272374329734,
"tokens": 148,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.06
},
{
"task": "HumanEval/6",
"ok": true,
"grund": "",
"tps": 19.360224750697995,
"tokens": 198,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.69
},
{
"task": "HumanEval/7",
"ok": true,
"grund": "",
"tps": 19.336421016412647,
"tokens": 107,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.01
},
{
"task": "HumanEval/8",
"ok": true,
"grund": "",
"tps": 18.82949203750835,
"tokens": 158,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.87
},
{
"task": "HumanEval/9",
"ok": true,
"grund": "",
"tps": 19.56911404372754,
"tokens": 166,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.96
},
{
"task": "HumanEval/10",
"ok": true,
"grund": "",
"tps": 19.563054966663596,
"tokens": 163,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.0
},
{
"task": "HumanEval/11",
"ok": true,
"grund": "",
"tps": 19.932230416583614,
"tokens": 105,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.91
},
{
"task": "HumanEval/12",
"ok": true,
"grund": "",
"tps": 19.607452426023713,
"tokens": 123,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.85
},
{
"task": "HumanEval/13",
"ok": true,
"grund": "",
"tps": 19.805330820065556,
"tokens": 92,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.21
},
{
"task": "HumanEval/14",
"ok": true,
"grund": "",
"tps": 19.776109408446498,
"tokens": 79,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.58
},
{
"task": "HumanEval/15",
"ok": true,
"grund": "",
"tps": 19.928326742096527,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.97
},
{
"task": "HumanEval/16",
"ok": true,
"grund": "",
"tps": 19.414306146748142,
"tokens": 76,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.51
},
{
"task": "HumanEval/17",
"ok": true,
"grund": "",
"tps": 19.39550515952364,
"tokens": 243,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.06
},
{
"task": "HumanEval/18",
"ok": true,
"grund": "",
"tps": 19.416226264752442,
"tokens": 156,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.51
},
{
"task": "HumanEval/19",
"ok": true,
"grund": "",
"tps": 19.282803443233796,
"tokens": 240,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.94
},
{
"task": "HumanEval/20",
"ok": true,
"grund": "",
"tps": 19.705825843587654,
"tokens": 268,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.13
},
{
"task": "HumanEval/21",
"ok": true,
"grund": "",
"tps": 19.65563535952614,
"tokens": 188,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.24
},
{
"task": "HumanEval/22",
"ok": true,
"grund": "",
"tps": 19.699850315698743,
"tokens": 114,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.48
},
{
"task": "HumanEval/23",
"ok": true,
"grund": "",
"tps": 20.392548053127687,
"tokens": 48,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.9
},
{
"task": "HumanEval/24",
"ok": true,
"grund": "",
"tps": 19.364236263763846,
"tokens": 81,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.77
},
{
"task": "HumanEval/25",
"ok": true,
"grund": "",
"tps": 19.379412197834878,
"tokens": 197,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.67
},
{
"task": "HumanEval/26",
"ok": true,
"grund": "",
"tps": 19.237882833868394,
"tokens": 114,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.37
},
{
"task": "HumanEval/27",
"ok": true,
"grund": "",
"tps": 19.362258355362467,
"tokens": 53,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.37
},
{
"task": "HumanEval/28",
"ok": true,
"grund": "",
"tps": 19.11917096921549,
"tokens": 65,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.86
},
{
"task": "HumanEval/29",
"ok": true,
"grund": "",
"tps": 20.06810958997901,
"tokens": 102,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.58
},
{
"task": "HumanEval/30",
"ok": true,
"grund": "",
"tps": 19.385718656801167,
"tokens": 134,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.62
},
{
"task": "HumanEval/31",
"ok": true,
"grund": "",
"tps": 20.178194699400656,
"tokens": 190,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.02
},
{
"task": "HumanEval/32",
"ok": false,
"grund": "TypeError: Value after * must be an iterable, not float",
"tps": 19.455250375129037,
"tokens": 893,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 46.55
},
{
"task": "HumanEval/33",
"ok": true,
"grund": "",
"tps": 19.88828901049643,
"tokens": 221,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.83
},
{
"task": "HumanEval/34",
"ok": true,
"grund": "",
"tps": 20.31304885486426,
"tokens": 82,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.5
},
{
"task": "HumanEval/35",
"ok": true,
"grund": "",
"tps": 19.47310436208121,
"tokens": 92,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.19
},
{
"task": "HumanEval/36",
"ok": true,
"grund": "",
"tps": 20.051022370207413,
"tokens": 134,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.33
},
{
"task": "HumanEval/37",
"ok": true,
"grund": "",
"tps": 19.58573512842337,
"tokens": 199,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.68
},
{
"task": "HumanEval/38",
"ok": true,
"grund": "",
"tps": 19.618669521112512,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.82
},
{
"task": "HumanEval/39",
"ok": true,
"grund": "",
"tps": 19.724429004642378,
"tokens": 257,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.72
},
{
"task": "HumanEval/40",
"ok": true,
"grund": "",
"tps": 19.387419907828836,
"tokens": 230,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.42
},
{
"task": "HumanEval/41",
"ok": true,
"grund": "",
"tps": 19.710596054662222,
"tokens": 158,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.8
},
{
"task": "HumanEval/42",
"ok": true,
"grund": "",
"tps": 20.02244405618771,
"tokens": 127,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.03
},
{
"task": "HumanEval/43",
"ok": true,
"grund": "",
"tps": 19.69232945588687,
"tokens": 196,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.5
},
{
"task": "HumanEval/44",
"ok": true,
"grund": "",
"tps": 19.39771489847198,
"tokens": 153,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.56
},
{
"task": "HumanEval/45",
"ok": true,
"grund": "",
"tps": 20.377733980601935,
"tokens": 53,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.2
},
{
"task": "HumanEval/46",
"ok": true,
"grund": "",
"tps": 19.380963225062757,
"tokens": 308,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 16.62
},
{
"task": "HumanEval/47",
"ok": true,
"grund": "",
"tps": 20.015681250966278,
"tokens": 145,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.85
},
{
"task": "HumanEval/48",
"ok": true,
"grund": "",
"tps": 19.735652962502016,
"tokens": 82,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.77
},
{
"task": "HumanEval/49",
"ok": true,
"grund": "",
"tps": 19.779039002425005,
"tokens": 129,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.19
},
{
"task": "HumanEval/50",
"ok": true,
"grund": "",
"tps": 19.660004792126166,
"tokens": 64,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.92
},
{
"task": "HumanEval/51",
"ok": true,
"grund": "",
"tps": 19.582654467978443,
"tokens": 160,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.86
},
{
"task": "HumanEval/52",
"ok": true,
"grund": "",
"tps": 19.376109664701524,
"tokens": 95,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.55
},
{
"task": "HumanEval/53",
"ok": true,
"grund": "",
"tps": 20.77265688011885,
"tokens": 58,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.39
},
{
"task": "HumanEval/54",
"ok": true,
"grund": "",
"tps": 19.812248465408004,
"tokens": 156,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.41
},
{
"task": "HumanEval/55",
"ok": true,
"grund": "",
"tps": 19.555181089357678,
"tokens": 105,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.0
},
{
"task": "HumanEval/56",
"ok": true,
"grund": "",
"tps": 20.15899899175789,
"tokens": 69,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.1
},
{
"task": "HumanEval/57",
"ok": true,
"grund": "",
"tps": 19.70729920943795,
"tokens": 158,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.52
},
{
"task": "HumanEval/58",
"ok": true,
"grund": "",
"tps": 19.76022909173044,
"tokens": 137,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.65
},
{
"task": "HumanEval/59",
"ok": true,
"grund": "",
"tps": 19.362225881487337,
"tokens": 132,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.56
},
{
"task": "HumanEval/60",
"ok": true,
"grund": "",
"tps": 19.875006086720614,
"tokens": 120,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.55
},
{
"task": "HumanEval/61",
"ok": true,
"grund": "",
"tps": 19.05434906053226,
"tokens": 151,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.71
},
{
"task": "HumanEval/62",
"ok": true,
"grund": "",
"tps": 19.704628970669592,
"tokens": 145,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.05
},
{
"task": "HumanEval/63",
"ok": true,
"grund": "",
"tps": 20.065535410653617,
"tokens": 234,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.2
},
{
"task": "HumanEval/64",
"ok": true,
"grund": "",
"tps": 19.473313801193896,
"tokens": 192,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.39
},
{
"task": "HumanEval/65",
"ok": true,
"grund": "",
"tps": 19.570426223436435,
"tokens": 67,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.09
},
{
"task": "HumanEval/66",
"ok": true,
"grund": "",
"tps": 23.86430323285377,
"tokens": 22,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.69
},
{
"task": "HumanEval/67",
"ok": true,
"grund": "",
"tps": 19.668638083400488,
"tokens": 36,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.63
},
{
"task": "HumanEval/68",
"ok": true,
"grund": "",
"tps": 19.587875651610045,
"tokens": 86,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.13
},
{
"task": "HumanEval/69",
"ok": true,
"grund": "",
"tps": 19.83893418925167,
"tokens": 226,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.95
},
{
"task": "HumanEval/70",
"ok": true,
"grund": "",
"tps": 19.512879042192264,
"tokens": 54,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.3
},
{
"task": "HumanEval/71",
"ok": true,
"grund": "",
"tps": 19.41853333238609,
"tokens": 205,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.09
},
{
"task": "HumanEval/72",
"ok": true,
"grund": "",
"tps": 20.382074210316915,
"tokens": 25,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.93
},
{
"task": "HumanEval/73",
"ok": true,
"grund": "",
"tps": 19.770795718590787,
"tokens": 205,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.0
},
{
"task": "HumanEval/74",
"ok": true,
"grund": "",
"tps": 19.765488653837423,
"tokens": 64,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.0
},
{
"task": "HumanEval/75",
"ok": true,
"grund": "",
"tps": 19.40254090323244,
"tokens": 145,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.13
},
{
"task": "HumanEval/76",
"ok": false,
"grund": "AssertionError",
"tps": 19.411058404345454,
"tokens": 77,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.51
},
{
"task": "HumanEval/77",
"ok": true,
"grund": "",
"tps": 20.15429755242461,
"tokens": 43,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.82
},
{
"task": "HumanEval/78",
"ok": true,
"grund": "",
"tps": 21.050302609296978,
"tokens": 47,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.09
},
{
"task": "HumanEval/79",
"ok": true,
"grund": "",
"tps": 20.573922999856876,
"tokens": 23,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.65
},
{
"task": "HumanEval/80",
"ok": true,
"grund": "",
"tps": 19.408718498500676,
"tokens": 76,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.44
},
{
"task": "HumanEval/81",
"ok": true,
"grund": "",
"tps": 19.50007309741687,
"tokens": 525,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 27.75
},
{
"task": "HumanEval/82",
"ok": true,
"grund": "",
"tps": 19.65045524578114,
"tokens": 64,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.91
},
{
"task": "HumanEval/83",
"ok": false,
"grund": "AssertionError",
"tps": 19.197097928368343,
"tokens": 174,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.68
},
{
"task": "HumanEval/84",
"ok": true,
"grund": "",
"tps": 19.277955734729158,
"tokens": 175,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.76
},
{
"task": "HumanEval/85",
"ok": true,
"grund": "",
"tps": 19.332745431532498,
"tokens": 83,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.74
},
{
"task": "HumanEval/86",
"ok": true,
"grund": "",
"tps": 19.72305090254995,
"tokens": 179,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 9.6
},
{
"task": "HumanEval/87",
"ok": true,
"grund": "",
"tps": 18.343267940912348,
"tokens": 69,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.41
},
{
"task": "HumanEval/88",
"ok": true,
"grund": "",
"tps": 20.214666502740084,
"tokens": 61,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.87
},
{
"task": "HumanEval/89",
"ok": true,
"grund": "",
"tps": 18.86983512995338,
"tokens": 101,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.09
},
{
"task": "HumanEval/90",
"ok": true,
"grund": "",
"tps": 19.414757982352366,
"tokens": 153,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.41
},
{
"task": "HumanEval/91",
"ok": false,
"grund": "AssertionError",
"tps": 19.921182569985607,
"tokens": 164,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.91
},
{
"task": "HumanEval/92",
"ok": true,
"grund": "",
"tps": 19.44854724754435,
"tokens": 54,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.47
},
{
"task": "HumanEval/93",
"ok": false,
"grund": "AssertionError",
"tps": 19.582872938012493,
"tokens": 264,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.0
},
{
"task": "HumanEval/94",
"ok": true,
"grund": "",
"tps": 19.481605688063933,
"tokens": 469,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 24.76
},
{
"task": "HumanEval/95",
"ok": true,
"grund": "",
"tps": 20.083974642209903,
"tokens": 85,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.81
},
{
"task": "HumanEval/96",
"ok": true,
"grund": "",
"tps": 19.6017840700917,
"tokens": 293,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.67
},
{
"task": "HumanEval/97",
"ok": false,
"grund": "AssertionError",
"tps": 20.57010456195551,
"tokens": 25,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.9
},
{
"task": "HumanEval/98",
"ok": true,
"grund": "",
"tps": 19.71771724891239,
"tokens": 121,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.79
},
{
"task": "HumanEval/99",
"ok": true,
"grund": "",
"tps": 19.412724083671574,
"tokens": 213,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 11.58
},
{
"task": "HumanEval/100",
"ok": true,
"grund": "",
"tps": 19.469861565447847,
"tokens": 203,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.96
},
{
"task": "HumanEval/101",
"ok": false,
"grund": "AssertionError",
"tps": 19.39444229988204,
"tokens": 135,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.58
},
{
"task": "HumanEval/102",
"ok": true,
"grund": "",
"tps": 19.091071690434454,
"tokens": 160,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.89
},
{
"task": "HumanEval/103",
"ok": true,
"grund": "",
"tps": 18.720494872212274,
"tokens": 46,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.01
},
{
"task": "HumanEval/104",
"ok": true,
"grund": "",
"tps": 19.334154043385098,
"tokens": 52,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.2
},
{
"task": "HumanEval/105",
"ok": true,
"grund": "",
"tps": 19.13884827534865,
"tokens": 127,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.47
},
{
"task": "HumanEval/106",
"ok": true,
"grund": "",
"tps": 19.23760647137117,
"tokens": 241,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 13.06
},
{
"task": "HumanEval/107",
"ok": true,
"grund": "",
"tps": 19.254816250667396,
"tokens": 310,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 16.78
},
{
"task": "HumanEval/108",
"ok": false,
"grund": "AssertionError",
"tps": 19.002828440601814,
"tokens": 102,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.91
},
{
"task": "HumanEval/109",
"ok": true,
"grund": "",
"tps": 19.457475056527755,
"tokens": 77,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.69
},
{
"task": "HumanEval/110",
"ok": true,
"grund": "",
"tps": 19.24610927872112,
"tokens": 280,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.14
},
{
"task": "HumanEval/111",
"ok": true,
"grund": "",
"tps": 19.467983358620895,
"tokens": 265,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.16
},
{
"task": "HumanEval/112",
"ok": true,
"grund": "",
"tps": 19.435743593164712,
"tokens": 37,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.63
},
{
"task": "HumanEval/113",
"ok": true,
"grund": "",
"tps": 19.405122534392593,
"tokens": 260,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.02
},
{
"task": "HumanEval/114",
"ok": true,
"grund": "",
"tps": 20.01582966185829,
"tokens": 70,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.15
},
{
"task": "HumanEval/115",
"ok": true,
"grund": "",
"tps": 19.222038802150976,
"tokens": 382,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 20.56
},
{
"task": "HumanEval/116",
"ok": true,
"grund": "",
"tps": 23.752101147409192,
"tokens": 26,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.91
},
{
"task": "HumanEval/117",
"ok": true,
"grund": "",
"tps": 19.227478649786182,
"tokens": 268,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.75
},
{
"task": "HumanEval/118",
"ok": true,
"grund": "",
"tps": 19.46826291482894,
"tokens": 278,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 15.02
},
{
"task": "HumanEval/119",
"ok": true,
"grund": "",
"tps": 19.722029691014292,
"tokens": 118,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.73
},
{
"task": "HumanEval/120",
"ok": true,
"grund": "",
"tps": 19.058932247597415,
"tokens": 263,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.41
},
{
"task": "HumanEval/121",
"ok": true,
"grund": "",
"tps": 19.31213397471076,
"tokens": 36,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.37
},
{
"task": "HumanEval/122",
"ok": true,
"grund": "",
"tps": 23.60752954285593,
"tokens": 30,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.05
},
{
"task": "HumanEval/123",
"ok": true,
"grund": "",
"tps": 19.31790480595901,
"tokens": 328,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 17.59
},
{
"task": "HumanEval/124",
"ok": false,
"grund": "AssertionError",
"tps": 19.563439444960444,
"tokens": 529,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 27.7
},
{
"task": "HumanEval/125",
"ok": false,
"grund": "AssertionError",
"tps": 19.571324994449167,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.18
},
{
"task": "HumanEval/126",
"ok": true,
"grund": "",
"tps": 18.67056559581316,
"tokens": 87,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.29
},
{
"task": "HumanEval/127",
"ok": false,
"grund": "AssertionError",
"tps": 19.451071777775773,
"tokens": 123,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.97
},
{
"task": "HumanEval/128",
"ok": true,
"grund": "",
"tps": 19.250896939816627,
"tokens": 95,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.64
},
{
"task": "HumanEval/129",
"ok": false,
"grund": "SyntaxError: invalid syntax",
"tps": 19.33404899389798,
"tokens": 1200,
"denk_zeichen": 0,
"abbruch": "length",
"sekunden": 62.83
},
{
"task": "HumanEval/130",
"ok": false,
"grund": "IndexError: list index out of range",
"tps": 19.10760534804503,
"tokens": 407,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 22.18
},
{
"task": "HumanEval/131",
"ok": true,
"grund": "",
"tps": 19.66948010840607,
"tokens": 65,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.95
},
{
"task": "HumanEval/132",
"ok": false,
"grund": "AssertionError",
"tps": 19.68258861611245,
"tokens": 83,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.81
},
{
"task": "HumanEval/133",
"ok": true,
"grund": "",
"tps": 19.494331785940012,
"tokens": 185,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.16
},
{
"task": "HumanEval/134",
"ok": true,
"grund": "",
"tps": 19.396694116356322,
"tokens": 96,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.68
},
{
"task": "HumanEval/135",
"ok": true,
"grund": "",
"tps": 19.978556349518183,
"tokens": 48,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.02
},
{
"task": "HumanEval/136",
"ok": true,
"grund": "",
"tps": 19.41820006571528,
"tokens": 76,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.63
},
{
"task": "HumanEval/137",
"ok": true,
"grund": "",
"tps": 20.086770481792104,
"tokens": 92,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.26
},
{
"task": "HumanEval/138",
"ok": true,
"grund": "",
"tps": 23.744109729445764,
"tokens": 24,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 1.73
},
{
"task": "HumanEval/139",
"ok": true,
"grund": "",
"tps": 19.27467618226996,
"tokens": 152,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.55
},
{
"task": "HumanEval/140",
"ok": false,
"grund": "AssertionError",
"tps": 18.48278513392626,
"tokens": 30,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.32
},
{
"task": "HumanEval/141",
"ok": false,
"grund": "AssertionError",
"tps": 19.083887006105403,
"tokens": 159,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.94
},
{
"task": "HumanEval/142",
"ok": true,
"grund": "",
"tps": 18.91578793459023,
"tokens": 74,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.46
},
{
"task": "HumanEval/143",
"ok": true,
"grund": "",
"tps": 19.363216611347248,
"tokens": 125,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.28
},
{
"task": "HumanEval/144",
"ok": true,
"grund": "",
"tps": 19.03965185996574,
"tokens": 64,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.91
},
{
"task": "HumanEval/145",
"ok": false,
"grund": "AssertionError",
"tps": 19.023001691317788,
"tokens": 33,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.26
},
{
"task": "HumanEval/146",
"ok": true,
"grund": "",
"tps": 19.61314167661852,
"tokens": 90,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 5.35
},
{
"task": "HumanEval/147",
"ok": true,
"grund": "",
"tps": 19.252622528065363,
"tokens": 1155,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 60.55
},
{
"task": "HumanEval/148",
"ok": true,
"grund": "",
"tps": 19.9915872800194,
"tokens": 123,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.0
},
{
"task": "HumanEval/149",
"ok": true,
"grund": "",
"tps": 20.010253529912223,
"tokens": 232,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 12.44
},
{
"task": "HumanEval/150",
"ok": true,
"grund": "",
"tps": 18.968350965257077,
"tokens": 139,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.07
},
{
"task": "HumanEval/151",
"ok": true,
"grund": "",
"tps": 19.5377762904576,
"tokens": 39,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.77
},
{
"task": "HumanEval/152",
"ok": true,
"grund": "",
"tps": 18.709356621205327,
"tokens": 26,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 2.03
},
{
"task": "HumanEval/153",
"ok": true,
"grund": "",
"tps": 19.07308709162809,
"tokens": 78,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 4.96
},
{
"task": "HumanEval/154",
"ok": false,
"grund": "AssertionError",
"tps": 20.259319286871964,
"tokens": 161,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.77
},
{
"task": "HumanEval/155",
"ok": true,
"grund": "",
"tps": 19.604015341033097,
"tokens": 143,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 7.93
},
{
"task": "HumanEval/156",
"ok": true,
"grund": "",
"tps": 19.243234221390235,
"tokens": 297,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 16.12
},
{
"task": "HumanEval/157",
"ok": true,
"grund": "",
"tps": 19.256623590778673,
"tokens": 147,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.17
},
{
"task": "HumanEval/158",
"ok": true,
"grund": "",
"tps": 19.54881745251873,
"tokens": 188,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 10.26
},
{
"task": "HumanEval/159",
"ok": true,
"grund": "",
"tps": 19.302130329018027,
"tokens": 336,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 18.36
},
{
"task": "HumanEval/160",
"ok": true,
"grund": "",
"tps": 19.79395612090746,
"tokens": 265,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 14.18
},
{
"task": "HumanEval/161",
"ok": true,
"grund": "",
"tps": 21.109079479483874,
"tokens": 50,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 3.16
},
{
"task": "HumanEval/162",
"ok": true,
"grund": "",
"tps": 20.32045181756196,
"tokens": 119,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 6.59
},
{
"task": "HumanEval/163",
"ok": false,
"grund": "Zeitueberschreitung (25s)",
"tps": 20.208351970282138,
"tokens": 157,
"denk_zeichen": 0,
"abbruch": "stop",
"sekunden": 8.45
}
]
}