fev-bench / tables /domain_cloud /pairwise_SQL.csv
shchuro's picture
Update results per group
169601b
model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,Chronos-2,0.6,0.4,0.8,-0.024,-0.08,0.018
Toto-1.0,TimesFM-2.5,0.75,0.55,0.95,0.028,-0.024,0.076
Toto-1.0,TiRex,0.8,0.6,0.95,0.056,0.022,0.104
Toto-1.0,Moirai-2.0,0.95,0.85,1.0,0.112,0.064,0.169
Toto-1.0,Sundial-Base,0.95,0.85,1.0,0.148,0.071,0.211
Toto-1.0,Chronos-Bolt,0.95,0.85,1.0,0.182,0.124,0.236
Toto-1.0,TabPFN-TS,0.85,0.65,1.0,0.213,0.131,0.291
Toto-1.0,AutoARIMA,1.0,1.0,1.0,0.452,0.369,0.537
Toto-1.0,Stat. Ensemble,1.0,1.0,1.0,0.538,0.448,0.619
Toto-1.0,AutoETS,1.0,1.0,1.0,0.666,0.482,0.815
Toto-1.0,AutoTheta,1.0,1.0,1.0,0.638,0.54,0.72
Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.631,0.521,0.73
Toto-1.0,Naive,1.0,1.0,1.0,0.817,0.735,0.877
Toto-1.0,Drift,1.0,1.0,1.0,0.824,0.744,0.882
Chronos-2,Toto-1.0,0.4,0.2,0.6,0.024,-0.018,0.074
Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-2,TimesFM-2.5,0.75,0.55,0.9,0.051,0.017,0.09
Chronos-2,TiRex,0.75,0.55,0.9,0.078,0.024,0.139
Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.133,0.069,0.2
Chronos-2,Sundial-Base,0.95,0.85,1.0,0.168,0.118,0.222
Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.201,0.134,0.261
Chronos-2,TabPFN-TS,0.95,0.85,1.0,0.232,0.162,0.3
Chronos-2,AutoARIMA,1.0,1.0,1.0,0.465,0.381,0.55
Chronos-2,Stat. Ensemble,1.0,1.0,1.0,0.549,0.47,0.623
Chronos-2,AutoETS,1.0,1.0,1.0,0.674,0.501,0.819
Chronos-2,AutoTheta,1.0,1.0,1.0,0.647,0.555,0.727
Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.639,0.533,0.735
Chronos-2,Naive,1.0,1.0,1.0,0.822,0.746,0.879
Chronos-2,Drift,1.0,1.0,1.0,0.828,0.756,0.883
TimesFM-2.5,Toto-1.0,0.25,0.05,0.45,-0.029,-0.082,0.024
TimesFM-2.5,Chronos-2,0.25,0.1,0.45,-0.054,-0.099,-0.017
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,TiRex,0.6,0.4,0.8,0.028,-0.014,0.08
TimesFM-2.5,Moirai-2.0,0.9,0.75,1.0,0.086,0.038,0.143
TimesFM-2.5,Sundial-Base,0.95,0.85,1.0,0.123,0.079,0.165
TimesFM-2.5,Chronos-Bolt,0.9,0.75,1.0,0.158,0.095,0.217
TimesFM-2.5,TabPFN-TS,0.85,0.7,1.0,0.19,0.124,0.257
TimesFM-2.5,AutoARIMA,1.0,1.0,1.0,0.436,0.367,0.511
TimesFM-2.5,Stat. Ensemble,1.0,1.0,1.0,0.524,0.451,0.594
TimesFM-2.5,AutoETS,1.0,1.0,1.0,0.657,0.476,0.811
TimesFM-2.5,AutoTheta,1.0,1.0,1.0,0.628,0.534,0.71
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.62,0.519,0.713
TimesFM-2.5,Naive,1.0,1.0,1.0,0.812,0.731,0.872
TimesFM-2.5,Drift,1.0,1.0,1.0,0.819,0.742,0.877
TiRex,Toto-1.0,0.2,0.05,0.4,-0.059,-0.116,-0.023
TiRex,Chronos-2,0.25,0.1,0.45,-0.085,-0.162,-0.025
TiRex,TimesFM-2.5,0.4,0.2,0.6,-0.029,-0.086,0.013
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,Moirai-2.0,0.85,0.7,1.0,0.059,0.03,0.09
TiRex,Sundial-Base,0.95,0.85,1.0,0.097,0.013,0.151
TiRex,Chronos-Bolt,0.9,0.75,1.0,0.133,0.073,0.186
TiRex,TabPFN-TS,0.75,0.55,0.95,0.166,0.079,0.247
TiRex,AutoARIMA,1.0,1.0,1.0,0.42,0.343,0.497
TiRex,Stat. Ensemble,1.0,1.0,1.0,0.51,0.425,0.585
TiRex,AutoETS,1.0,1.0,1.0,0.647,0.453,0.808
TiRex,AutoTheta,1.0,1.0,1.0,0.617,0.513,0.698
TiRex,Seasonal Naive,1.0,1.0,1.0,0.609,0.499,0.709
TiRex,Naive,0.95,0.85,1.0,0.806,0.72,0.869
TiRex,Drift,1.0,1.0,1.0,0.814,0.729,0.874
Moirai-2.0,Toto-1.0,0.05,0.0,0.15,-0.126,-0.203,-0.068
Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.153,-0.249,-0.074
Moirai-2.0,TimesFM-2.5,0.1,0.0,0.25,-0.094,-0.167,-0.039
Moirai-2.0,TiRex,0.15,0.0,0.3,-0.063,-0.099,-0.03
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Sundial-Base,0.9,0.75,1.0,0.041,-0.045,0.091
Moirai-2.0,Chronos-Bolt,0.8,0.6,0.95,0.079,0.017,0.14
Moirai-2.0,TabPFN-TS,0.75,0.55,0.901,0.114,0.03,0.194
Moirai-2.0,AutoARIMA,1.0,1.0,1.0,0.383,0.305,0.459
Moirai-2.0,Stat. Ensemble,0.95,0.85,1.0,0.48,0.391,0.559
Moirai-2.0,AutoETS,0.95,0.85,1.0,0.628,0.423,0.798
Moirai-2.0,AutoTheta,0.95,0.85,1.0,0.593,0.49,0.673
Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.584,0.469,0.689
Moirai-2.0,Naive,0.95,0.85,1.0,0.794,0.704,0.859
Moirai-2.0,Drift,1.0,1.0,1.0,0.802,0.716,0.864
Sundial-Base,Toto-1.0,0.05,0.0,0.15,-0.174,-0.268,-0.077
Sundial-Base,Chronos-2,0.05,0.0,0.15,-0.202,-0.285,-0.134
Sundial-Base,TimesFM-2.5,0.05,0.0,0.15,-0.14,-0.198,-0.085
Sundial-Base,TiRex,0.05,0.0,0.15,-0.108,-0.178,-0.013
Sundial-Base,Moirai-2.0,0.1,0.0,0.25,-0.043,-0.1,0.043
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,Chronos-Bolt,0.4,0.2,0.6,0.04,-0.037,0.117
Sundial-Base,TabPFN-TS,0.65,0.45,0.85,0.076,0.006,0.138
Sundial-Base,AutoARIMA,1.0,1.0,1.0,0.357,0.281,0.436
Sundial-Base,Stat. Ensemble,1.0,1.0,1.0,0.457,0.378,0.534
Sundial-Base,AutoETS,1.0,1.0,1.0,0.615,0.404,0.793
Sundial-Base,AutoTheta,1.0,1.0,1.0,0.575,0.487,0.657
Sundial-Base,Seasonal Naive,1.0,1.0,1.0,0.566,0.454,0.668
Sundial-Base,Naive,1.0,1.0,1.0,0.786,0.704,0.848
Sundial-Base,Drift,1.0,1.0,1.0,0.794,0.716,0.854
Chronos-Bolt,Toto-1.0,0.05,0.0,0.15,-0.222,-0.31,-0.142
Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.251,-0.352,-0.155
Chronos-Bolt,TimesFM-2.5,0.1,0.0,0.25,-0.187,-0.277,-0.105
Chronos-Bolt,TiRex,0.1,0.0,0.25,-0.154,-0.229,-0.079
Chronos-Bolt,Moirai-2.0,0.2,0.05,0.4,-0.086,-0.162,-0.017
Chronos-Bolt,Sundial-Base,0.6,0.4,0.8,-0.041,-0.133,0.036
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,TabPFN-TS,0.7,0.5,0.851,0.038,-0.082,0.139
Chronos-Bolt,AutoARIMA,0.9,0.75,1.0,0.33,0.236,0.434
Chronos-Bolt,Stat. Ensemble,0.85,0.7,1.0,0.435,0.328,0.531
Chronos-Bolt,AutoETS,0.9,0.75,1.0,0.597,0.372,0.786
Chronos-Bolt,AutoTheta,0.95,0.85,1.0,0.558,0.453,0.645
Chronos-Bolt,Seasonal Naive,0.9,0.75,1.0,0.549,0.413,0.67
Chronos-Bolt,Naive,0.95,0.85,1.0,0.777,0.686,0.844
Chronos-Bolt,Drift,1.0,1.0,1.0,0.785,0.7,0.851
TabPFN-TS,Toto-1.0,0.15,0.0,0.35,-0.271,-0.41,-0.151
TabPFN-TS,Chronos-2,0.05,0.0,0.15,-0.301,-0.429,-0.193
TabPFN-TS,TimesFM-2.5,0.15,0.0,0.3,-0.235,-0.346,-0.141
TabPFN-TS,TiRex,0.25,0.05,0.45,-0.2,-0.328,-0.086
TabPFN-TS,Moirai-2.0,0.25,0.099,0.45,-0.129,-0.24,-0.03
TabPFN-TS,Sundial-Base,0.35,0.15,0.55,-0.083,-0.161,-0.006
TabPFN-TS,Chronos-Bolt,0.3,0.149,0.5,-0.04,-0.162,0.076
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,AutoARIMA,0.9,0.75,1.0,0.304,0.205,0.404
TabPFN-TS,Stat. Ensemble,0.9,0.75,1.0,0.412,0.312,0.505
TabPFN-TS,AutoETS,0.85,0.7,1.0,0.586,0.354,0.779
TabPFN-TS,AutoTheta,0.95,0.85,1.0,0.54,0.433,0.639
TabPFN-TS,Seasonal Naive,0.95,0.85,1.0,0.531,0.407,0.643
TabPFN-TS,Naive,1.0,1.0,1.0,0.768,0.681,0.835
TabPFN-TS,Drift,1.0,1.0,1.0,0.777,0.696,0.841
AutoARIMA,Toto-1.0,0.0,0.0,0.0,-0.825,-1.161,-0.584
AutoARIMA,Chronos-2,0.0,0.0,0.0,-0.869,-1.222,-0.615
AutoARIMA,TimesFM-2.5,0.0,0.0,0.0,-0.773,-1.043,-0.58
AutoARIMA,TiRex,0.0,0.0,0.0,-0.723,-0.989,-0.521
AutoARIMA,Moirai-2.0,0.0,0.0,0.0,-0.621,-0.848,-0.438
AutoARIMA,Sundial-Base,0.0,0.0,0.0,-0.555,-0.773,-0.392
AutoARIMA,Chronos-Bolt,0.1,0.0,0.25,-0.493,-0.768,-0.309
AutoARIMA,TabPFN-TS,0.1,0.0,0.25,-0.436,-0.677,-0.258
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,Stat. Ensemble,0.725,0.525,0.875,0.156,0.073,0.244
AutoARIMA,AutoETS,0.775,0.6,0.95,0.434,0.08,0.713
AutoARIMA,AutoTheta,0.85,0.7,1.0,0.34,0.203,0.476
AutoARIMA,Seasonal Naive,0.875,0.75,0.975,0.326,0.18,0.457
AutoARIMA,Naive,0.95,0.85,1.0,0.667,0.521,0.764
AutoARIMA,Drift,0.95,0.85,1.0,0.679,0.545,0.773
Stat. Ensemble,Toto-1.0,0.0,0.0,0.0,-1.163,-1.625,-0.811
Stat. Ensemble,Chronos-2,0.0,0.0,0.0,-1.215,-1.654,-0.887
Stat. Ensemble,TimesFM-2.5,0.0,0.0,0.0,-1.102,-1.466,-0.82
Stat. Ensemble,TiRex,0.0,0.0,0.0,-1.042,-1.411,-0.739
Stat. Ensemble,Moirai-2.0,0.05,0.0,0.15,-0.921,-1.267,-0.642
Stat. Ensemble,Sundial-Base,0.0,0.0,0.0,-0.843,-1.145,-0.609
Stat. Ensemble,Chronos-Bolt,0.15,0.0,0.3,-0.77,-1.134,-0.488
Stat. Ensemble,TabPFN-TS,0.1,0.0,0.25,-0.702,-1.019,-0.454
Stat. Ensemble,AutoARIMA,0.275,0.125,0.475,-0.185,-0.323,-0.078
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoETS,0.725,0.55,0.9,0.363,-0.063,0.684
Stat. Ensemble,AutoTheta,0.9,0.75,1.0,0.218,0.089,0.375
Stat. Ensemble,Seasonal Naive,0.725,0.525,0.9,0.201,-0.013,0.369
Stat. Ensemble,Naive,0.95,0.85,1.0,0.605,0.443,0.725
Stat. Ensemble,Drift,1.0,1.0,1.0,0.62,0.465,0.735
AutoETS,Toto-1.0,0.0,0.0,0.0,-1.991,-4.394,-0.932
AutoETS,Chronos-2,0.0,0.0,0.0,-2.072,-4.534,-1.004
AutoETS,TimesFM-2.5,0.0,0.0,0.0,-1.92,-4.291,-0.907
AutoETS,TiRex,0.0,0.0,0.0,-1.837,-4.196,-0.83
AutoETS,Moirai-2.0,0.05,0.0,0.15,-1.688,-3.95,-0.734
AutoETS,Sundial-Base,0.0,0.0,0.0,-1.595,-3.825,-0.677
AutoETS,Chronos-Bolt,0.1,0.0,0.25,-1.484,-3.678,-0.591
AutoETS,TabPFN-TS,0.15,0.0,0.3,-1.414,-3.528,-0.549
AutoETS,AutoARIMA,0.225,0.05,0.4,-0.767,-2.48,-0.087
AutoETS,Stat. Ensemble,0.275,0.1,0.45,-0.569,-2.162,0.059
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,AutoTheta,0.75,0.55,0.9,-0.25,-1.708,0.289
AutoETS,Seasonal Naive,0.725,0.525,0.875,-0.269,-1.702,0.285
AutoETS,Naive,0.8,0.6,0.95,0.34,-0.612,0.679
AutoETS,Drift,0.85,0.65,1.0,0.363,-0.555,0.692
AutoTheta,Toto-1.0,0.0,0.0,0.0,-1.764,-2.575,-1.173
AutoTheta,Chronos-2,0.0,0.0,0.0,-1.831,-2.661,-1.245
AutoTheta,TimesFM-2.5,0.0,0.0,0.0,-1.686,-2.451,-1.145
AutoTheta,TiRex,0.0,0.0,0.0,-1.61,-2.316,-1.054
AutoTheta,Moirai-2.0,0.05,0.0,0.15,-1.456,-2.054,-0.962
AutoTheta,Sundial-Base,0.0,0.0,0.0,-1.355,-1.914,-0.951
AutoTheta,Chronos-Bolt,0.05,0.0,0.15,-1.262,-1.821,-0.828
AutoTheta,TabPFN-TS,0.05,0.0,0.15,-1.175,-1.772,-0.765
AutoTheta,AutoARIMA,0.15,0.0,0.3,-0.515,-0.908,-0.255
AutoTheta,Stat. Ensemble,0.1,0.0,0.25,-0.278,-0.6,-0.097
AutoTheta,AutoETS,0.25,0.1,0.45,0.2,-0.407,0.631
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,Seasonal Naive,0.7,0.5,0.9,-0.021,-0.413,0.245
AutoTheta,Naive,0.85,0.65,1.0,0.495,0.359,0.605
AutoTheta,Drift,0.9,0.75,1.0,0.514,0.382,0.62
Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-1.707,-2.709,-1.086
Seasonal Naive,Chronos-2,0.0,0.0,0.0,-1.772,-2.77,-1.139
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-1.631,-2.486,-1.077
Seasonal Naive,TiRex,0.0,0.0,0.0,-1.556,-2.437,-0.997
Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-1.405,-2.214,-0.883
Seasonal Naive,Sundial-Base,0.0,0.0,0.0,-1.307,-2.016,-0.832
Seasonal Naive,Chronos-Bolt,0.1,0.0,0.25,-1.215,-2.027,-0.704
Seasonal Naive,TabPFN-TS,0.05,0.0,0.15,-1.13,-1.801,-0.687
Seasonal Naive,AutoARIMA,0.125,0.025,0.25,-0.483,-0.841,-0.219
Seasonal Naive,Stat. Ensemble,0.275,0.1,0.475,-0.252,-0.585,0.013
Seasonal Naive,AutoETS,0.275,0.125,0.475,0.212,-0.398,0.63
Seasonal Naive,AutoTheta,0.3,0.1,0.5,0.021,-0.325,0.292
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Naive,0.7,0.525,0.85,0.505,0.274,0.671
Seasonal Naive,Drift,0.85,0.65,1.0,0.524,0.302,0.688
Naive,Toto-1.0,0.0,0.0,0.0,-4.472,-7.119,-2.772
Naive,Chronos-2,0.0,0.0,0.0,-4.604,-7.24,-2.94
Naive,TimesFM-2.5,0.0,0.0,0.0,-4.318,-6.839,-2.721
Naive,TiRex,0.05,0.0,0.15,-4.166,-6.661,-2.569
Naive,Moirai-2.0,0.05,0.0,0.15,-3.861,-6.072,-2.376
Naive,Sundial-Base,0.0,0.0,0.0,-3.663,-5.597,-2.374
Naive,Chronos-Bolt,0.05,0.0,0.15,-3.478,-5.427,-2.188
Naive,TabPFN-TS,0.0,0.0,0.0,-3.306,-5.057,-2.139
Naive,AutoARIMA,0.05,0.0,0.15,-1.999,-3.24,-1.086
Naive,Stat. Ensemble,0.05,0.0,0.15,-1.53,-2.642,-0.795
Naive,AutoETS,0.2,0.05,0.4,-0.516,-2.117,0.38
Naive,AutoTheta,0.15,0.0,0.35,-0.98,-1.531,-0.56
Naive,Seasonal Naive,0.3,0.15,0.475,-1.021,-2.041,-0.378
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Drift,1.0,1.0,1.0,0.039,0.023,0.057
Drift,Toto-1.0,0.0,0.0,0.0,-4.691,-7.48,-2.9
Drift,Chronos-2,0.0,0.0,0.0,-4.828,-7.54,-3.102
Drift,TimesFM-2.5,0.0,0.0,0.0,-4.531,-7.137,-2.871
Drift,TiRex,0.0,0.0,0.0,-4.373,-6.957,-2.696
Drift,Moirai-2.0,0.0,0.0,0.0,-4.056,-6.361,-2.518
Drift,Sundial-Base,0.0,0.0,0.0,-3.85,-5.831,-2.522
Drift,Chronos-Bolt,0.0,0.0,0.0,-3.658,-5.689,-2.332
Drift,TabPFN-TS,0.0,0.0,0.0,-3.479,-5.272,-2.287
Drift,AutoARIMA,0.05,0.0,0.15,-2.119,-3.399,-1.198
Drift,Stat. Ensemble,0.0,0.0,0.0,-1.632,-2.779,-0.87
Drift,AutoETS,0.15,0.0,0.35,-0.569,-2.25,0.357
Drift,AutoTheta,0.1,0.0,0.25,-1.059,-1.634,-0.617
Drift,Seasonal Naive,0.15,0.0,0.35,-1.102,-2.206,-0.433
Drift,Naive,0.0,0.0,0.0,-0.04,-0.061,-0.024
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0