Delete provokac.csv
Browse files- provokac.csv +0 -30
provokac.csv
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
Model,PROVOC_1_num_q_EM,PROVOC_1_num_q_CC,PROVOC_1_num_q_PM,PROVOC_1_open_q_EM,PROVOC_1_open_q_F1,PROVOC_1_open_q_LR,PROVOC_1_avg,PROVOC_2_num_q_EM,PROVOC_2_num_q_CC,PROVOC_2_num_q_PM,PROVOC_2_open_q_EM,PROVOC_2_open_q_F1,PROVOC_2_open_q_LR,PROVOC_2_avg,PROVOC_3_num_q_EM,PROVOC_3_num_q_CC,PROVOC_3_num_q_PM,PROVOC_3_open_q_EM,PROVOC_3_open_q_F1,PROVOC_3_open_q_LR,PROVOC_3_avg,PROVOC_avg
|
2 |
-
claude-3.5-sonnet,89.5348837209302,90.2823920265781,91.6112956810631,69.6428571428571,75.8213674084941,85.4196428571429,83.71873980617758,85.6,86.6666666666667,87.6666666666667,64.2857142857143,73.3268391254803,81.6428571428571,79.86479064789752,76.4705882352941,77.9831932773109,82.0168067226891,60.0,66.8166631845606,77.5052632,73.46541910330912,79.01631651912808
|
3 |
-
gpt-4o,83.1395348837209,85.0498338870432,86.3787375415282,23.2142857142857,70.4645569418623,80.3035714285714,71.42508673283528,78.2666666666667,79.7333333333333,82.3333333333333,7.14285714285714,63.7358690236676,73.2261904761905,64.07304166267475,64.7058823529412,66.7226890756302,72.6890756302521,7.36842105263158,60.5334838577312,70.8736842105263,57.148872696618774,64.21566703070961
|
4 |
-
gemma2:27b-instruct-q4_0,13.0885602583716,35.0501444841068,36.6054733979262,2.46710526315789,11.3438276640427,18.7450657894737,19.550029476179816,10.5151915455746,34.6895640686922,36.1426684280053,1.7353579175705,7.23438464320977,14.3036876355748,17.436809039771195,6.84281842818428,22.5948509485095,33.4688346883469,0.588235294117647,5.44191022355375,11.6352941176471,13.428657283393198,16.805165266448068
|
5 |
-
gemma2:9b-instruct-q4_0,55.4139044705082,60.4283528811831,64.5843957164712,27.3026315789474,34.9929958961886,52.3865131578947,49.184798950198875,55.2708058124174,60.105680317041,63.0779392338177,27.3318872017354,35.245661577345,52.6681127982647,48.950014490103534,44.2073170731707,52.4390243902439,56.8428184281843,18.4313725490196,25.6150995826153,44.0039215686275,40.25659226531022,46.13046856853753
|
6 |
-
gemma:7b-instruct-v1.1-q4_0,16.1652218255992,32.3814380418154,37.3363929967704,0.0,6.12514628005334,23.4473684210526,19.24259459421516,14.0290620871863,31.7040951122853,37.8071334214003,0.216919739696312,7.23992067543114,24.943600867679,19.323455317279723,8.87533875338753,22.9336043360434,33.6720867208672,0.0,4.83394851448634,22.8098039215686,15.520797041058843,18.028948984184574
|
7 |
-
ilyagusev/saiga_llama3,32.87438381778,35.5430902600714,49.7790243073262,6.41447368421053,20.8053473204584,38.7894736842105,30.700965512342844,33.8441215323646,36.4861294583884,49.4583883751651,9.54446854663774,25.5266537708331,44.7830802603037,33.27380699061544,19.8170731707317,26.1856368563686,45.2235772357724,5.09803921568627,20.0481873440546,39.2372549019608,25.934961454095728,29.969911319018006
|
8 |
-
llama-405b,3.48837209302326,58.1395349,65.9053156,7.14285714285714,40.9068319991679,59.1696428571429,39.1254257653652,4.53333333333333,59.3333333,64.6666666666667,2.38095238095238,50.9196057488653,62.8809523809524,40.785807301795025,6.38655462184874,40.672268907563,60.672268907563,3.1578947368421,39.494785325223,54.0736842105263,34.076242784927686,37.9958252840293
|
9 |
-
llama2:13b,0.0,24.1543430222675,9.55294917559069,0.0,2.83808861437468,8.72203947368421,7.544570047652848,0.0,15.9313077939234,9.85468956406869,0.0,5.93808858848223,14.4577006507592,7.696964432872253,0.0,11.7547425474255,17.5982384823848,0.196078431372549,7.24939909960657,16.978431372549,8.962814988889738,8.068116489804948
|
10 |
-
llama3.1:70b-instruct-q4_0,22.0975692673806,59.9864014958355,65.0263471018188,18.0921052631579,49.4000831972529,65.4835526315789,46.681009826170765,21.558784676354,59.9471598414795,64.2536327608983,12.5813449023861,52.9417050541935,65.1952277657267,46.079642500173016,21.1382113821138,51.219512195122,57.1815718157182,11.3725490196078,44.6480415518083,60.621568627451,41.03024243197018,44.59696491943799
|
11 |
-
llama3.1:8b-instruct-q4_0,4.11354750977393,29.3047764745878,38.2457929627741,0.657894736842105,16.8408300317768,39.21875,21.39693195262579,4.38573315719947,31.7569352708058,41.889035667107,0.216919739696312,23.6358923040094,41.9913232104121,23.979306558205014,2.710027100271,18.5636856368564,43.4959349593496,0.392156862745098,18.0908295632752,37.9745098039216,20.20452398773648,21.860254166189094
|
12 |
-
llama3:70b-instruct-q4_0,53.7650858405575,62.0941696413395,63.9129695733469,13.1578947368421,44.7874198858453,60.8569078947368,49.762407928778025,51.7569352708058,61.9286657859974,60.5019815059445,7.15835140997831,47.0840736221898,61.0976138828633,48.25460357962985,39.5325203252033,56.3008130081301,54.0650406504065,9.80392156862745,42.8576254770552,59.5039215686275,43.677307099675005,47.23143953602762
|
13 |
-
llama3:8b-instruct-q4_0,14.4144144144144,32.296447390787,47.5437701852796,0.164473684210526,14.8289590829379,32.9309210526316,23.696497635043503,13.5799207397622,33.8705416116248,49.0885072655218,0.0,21.1064741325482,39.5336225596529,26.196511051518314,6.30081300813008,19.579945799458,44.2581300813008,0.0,16.2142171491163,34.2176470588235,20.095125516138115,23.329378067566648
|
14 |
-
mistral:7b-instruct-v0.3-q4_0,23.6613972463029,28.0469148393677,45.3340132585416,1.97368421052632,11.6339867326757,25.5740131578947,22.704001574218154,24.4121532364597,31.8361955085865,46.4861294583884,2.16919739696312,11.9370897080079,26.0325379609544,23.81221721156,12.7032520325203,16.8021680216802,41.8529810298103,3.33333333333333,11.2589813397905,26.4862745098039,18.739498377823086,21.751905721200412
|
15 |
-
mixtral:8x7b-instruct-v0.1-q4_0,5.16743158252592,43.8551759306476,52.0652728199898,1.15131578947368,6.41044460793093,11.1595394736842,19.968196700708692,3.93659180977543,44.8348745046235,54.8612945838837,0.0,4.81190475632898,9.01301518438178,19.57628013983223,1.6260162601626,32.079945799458,49.1531165311653,0.588235294117647,4.08394916230811,9.03137254901961,16.09377259937188,18.5460831466376
|
16 |
-
phi3:14b-medium-4k-instruct-q4_0,29.5427502974673,38.6367499575047,60.2583715791263,5.09868421052632,17.0255729274497,30.3042763157895,30.14440088131064,28.1638044914135,41.5852047556143,58.5204755614267,6.941431670282,19.6178110192585,35.4880694143167,31.719466152051954,16.6327913279133,22.5609756097561,52.4220867208672,3.92156862745098,14.1475921869919,29.7803921568627,23.24423443830703,28.36936715722321
|
17 |
-
qwen2:72b-instruct-q4_0,72.9389767125616,78.7013428522863,78.2168961414244,10.8552631578947,44.3525005243567,58.4539473684211,57.25315445949081,67.6882430647292,74.7424042272127,73.0515191545575,5.85683297180043,45.8644120654459,58.1301518438178,54.22226055459392,56.4363143631436,67.2086720867209,67.8184281842818,9.41176470588235,38.8817905312052,54.5607843137255,49.05295903082655,53.509458014970434
|
18 |
-
qwen2:7b-instruct-q4_0,40.3705592384838,41.9683834778174,54.3770185279619,3.78289473684211,12.2433821762303,34.2121710526316,31.159068201661185,38.1770145310436,40.105680317041,53.553500660502,4.55531453362256,12.2532095018336,33.5726681127983,30.369564609473503,23.5772357723577,25.8807588075881,50.9993224932249,2.94117647058823,9.74641760239777,30.3843137254902,23.921537478607817,28.483390096580838
|
19 |
-
qwen:7b,19.496855345912,19.9898011218766,29.7977222505524,0.0,2.53149921250892,16.6134868421053,14.738227462159204,20.2113606340819,20.5284015852048,29.8546895640687,0.0,2.9492578357003,18.6898047722343,15.372252398548332,10.6029810298103,11.0772357723577,27.10027100271,0.0,1.87065931868442,16.2372549019608,11.148067004253868,13.752848954987138
|
20 |
-
solar:10.7b-instruct-v1-q4_0,22.7265000849906,31.7525072242053,48.6996430392657,2.96052631578947,12.611043103768,25.0707236842105,23.97015724203826,26.1558784676354,34.7159841479524,50.1453104359313,4.12147505422994,11.1460215172048,23.6637744034707,24.991407337737424,11.6531165311653,18.3265582655827,45.0033875338753,3.33333333333333,10.2843989247715,20.5039215686274,18.184119359559254,22.38189464644498
|
21 |
-
wavecut/vikhr:7b-instruct_0.4-Q4_1,16.9471358150603,20.9246982831888,31.2850586435492,9.70394736842105,18.138570599769,32.7384868421053,21.62298292534894,18.6261558784676,23.7252311756935,34.1479524438573,9.76138828633406,20.2412450317039,35.527114967462,23.671514630586397,9.72222222222222,12.8048780487805,32.6388888888889,10.5882352941176,19.2141238256413,35.043137254902,20.001914255758752,21.76547060389803
|
22 |
-
yi:6b,5.9323474417814,25.922148563658,19.8368179500255,0.164473684210526,1.66768509191218,8.45559210526316,10.329844139475128,7.84676354029062,27.2655217965654,21.664464993395,0.433839479392625,2.71018597592006,11.409978308026,11.888459015598285,3.89566395663957,18.360433604336,20.0542005420054,0.0,2.66425497076314,11.3882352941176,9.393798061310283,10.5373670721279
|
23 |
-
yi:9b,15.4682984871664,26.6020737718851,33.2313445520993,0.986842105263158,3.19675483677559,14.8717105263158,15.726170713250893,14.7952443857332,29.4848084544254,34.6235138705416,0.433839479392625,3.52530523130186,14.0694143167028,16.155354289682915,10.1964769647696,23.0691056910569,32.8590785907859,0.392156862745098,3.71036337636581,16.4176470588235,14.440804757424466,15.440776586786093
|
24 |
-
GigaChat_Lite,60.2159468438538,62.4584717607973,65.0332225913621,33.0357142857143,40.9633292643836,60.4375,53.69069745768518,54.6666666666667,56.6666666666667,60.1333333333333,34.5238095238095,42.2388149962259,62.6666666666667,51.815992975561464,41.8487394957983,45.2100840336134,52.0168067226891,30.5263157894737,38.0252714022117,53.821052631579,43.57471167922753,49.693800704158065
|
25 |
-
GigaChat_Plus,60.2159468438538,62.4584717607973,65.0332225913621,32.1428571428571,40.6589114935278,58.9017857142857,53.235199257780636,54.6666666666667,56.6666666666667,60.1333333333333,34.5238095238095,41.8542728148981,62.8809523809524,51.787616897721115,41.8487394957983,45.2100840336134,52.0168067226891,32.6315789473684,38.1823841355402,55.3263157894737,44.202651520747175,49.74182255874965
|
26 |
-
GigaChat_Pro,69.2691029900332,70.1827242524917,72.7159468438538,43.75,51.2258923889299,67.6160714285714,62.45995631731333,65.0666666666667,67.0666666666667,69.8,41.6666666666667,48.8871336719648,67.2976190476191,59.964125453263996,51.4285714285714,54.453781512605,58.9075630252101,36.8421052631579,42.3231189954232,58.3684210526316,50.3872602129332,57.60378066117019
|
27 |
-
yandexgpt_lite,44.9335548172757,45.8471760797342,60.6727574750831,30.3571428571429,54.3516030514378,67.375,50.58953904677895,45.8666666666667,46.2666666666667,60.4,33.3333333333333,50.0530790747819,66.6309523809524,50.4251163537335,23.5294117647059,24.7058823529412,50.2521008403361,32.6315789473684,44.307314479042,60.5578947368421,39.33069718687261,46.78178419579502
|
28 |
-
yandexgpt_pro,69.3521594684385,70.0996677740864,76.7441860465116,8.92857142857143,54.2402693529171,66.5,57.64414234508751,60.2666666666667,60.6666666666667,70.1333333333333,27.3809523809524,53.1044518132574,63.5595238095238,55.851932445066716,44.2016806722689,45.7142857142857,60.8403361344538,12.6315789473684,44.5947129451386,60.5157894736842,44.749730647866606,52.748601812673606
|
29 |
-
random,15.4513003569607,16.8111507734149,25.5141934387217,,,,19.258881523032432,14.3196829590489,15.4821664464993,23.3157199471598,,,,17.705856450902665,10.0271002710027,11.4837398373984,25.0338753387534,,,,15.5149051490515,17.49321437432887
|
30 |
-
Среднее значение,30.273512425772175,42.83215988522128,49.89646610641287,10.411654135338345,24.564839013466877,39.121381578947364,32.74537892061203,29.01308132642347,42.207431492807316,49.137123598550275,10.674723685569674,25.922666205237647,40.41948662328272,32.742551468379915,20.220807209688125,30.661256685288258,44.824913548909244,9.152528379772955,21.9115750810828,36.77915376676987,27.121843331274494,30.86992457342215
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|