fev-bench / tables /mini /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
Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-2,TiRex,0.75,0.55,0.95,0.136,0.06,0.217
Chronos-2,TimesFM-2.5,0.8,0.6,0.95,0.127,0.049,0.215
Chronos-2,Toto-1.0,0.75,0.55,0.9,0.143,0.056,0.234
Chronos-2,TabPFN-TS,0.85,0.7,1.0,0.091,0.024,0.158
Chronos-2,Moirai-2.0,0.95,0.85,1.0,0.162,0.082,0.243
Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.18,0.104,0.255
Chronos-2,Sundial-Base,0.9,0.75,1.0,0.216,0.139,0.287
Chronos-2,Stat. Ensemble,0.95,0.85,1.0,0.327,0.248,0.403
Chronos-2,AutoARIMA,0.95,0.85,1.0,0.296,0.22,0.371
Chronos-2,AutoETS,0.95,0.85,1.0,0.541,0.378,0.703
Chronos-2,AutoTheta,1.0,1.0,1.0,0.466,0.381,0.543
Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.511,0.425,0.58
Chronos-2,Naive,1.0,1.0,1.0,0.643,0.567,0.719
Chronos-2,Drift,1.0,1.0,1.0,0.641,0.56,0.72
TiRex,Chronos-2,0.25,0.05,0.45,-0.158,-0.277,-0.063
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,TimesFM-2.5,0.55,0.35,0.75,-0.01,-0.066,0.03
TiRex,Toto-1.0,0.65,0.4,0.85,0.008,-0.031,0.042
TiRex,TabPFN-TS,0.6,0.4,0.8,-0.053,-0.216,0.076
TiRex,Moirai-2.0,0.75,0.55,0.95,0.03,-0.001,0.062
TiRex,Chronos-Bolt,0.9,0.75,1.0,0.051,0.02,0.085
TiRex,Sundial-Base,0.8,0.6,0.95,0.093,-0.028,0.186
TiRex,Stat. Ensemble,0.95,0.85,1.0,0.221,0.148,0.295
TiRex,AutoARIMA,0.95,0.85,1.0,0.185,0.141,0.234
TiRex,AutoETS,0.9,0.75,1.0,0.47,0.277,0.659
TiRex,AutoTheta,1.0,1.0,1.0,0.382,0.282,0.465
TiRex,Seasonal Naive,1.0,1.0,1.0,0.434,0.349,0.509
TiRex,Naive,0.95,0.85,1.0,0.587,0.503,0.656
TiRex,Drift,1.0,1.0,1.0,0.584,0.501,0.656
TimesFM-2.5,Chronos-2,0.2,0.05,0.4,-0.146,-0.274,-0.051
TimesFM-2.5,TiRex,0.45,0.25,0.65,0.01,-0.031,0.062
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,Toto-1.0,0.475,0.275,0.7,0.018,-0.018,0.058
TimesFM-2.5,TabPFN-TS,0.65,0.4,0.85,-0.042,-0.218,0.092
TimesFM-2.5,Moirai-2.0,0.625,0.425,0.825,0.04,-0.01,0.096
TimesFM-2.5,Chronos-Bolt,0.775,0.575,0.95,0.06,0.009,0.121
TimesFM-2.5,Sundial-Base,0.85,0.7,1.0,0.102,-0.022,0.189
TimesFM-2.5,Stat. Ensemble,0.85,0.7,1.0,0.229,0.15,0.307
TimesFM-2.5,AutoARIMA,0.8,0.649,0.95,0.193,0.134,0.252
TimesFM-2.5,AutoETS,0.9,0.75,1.0,0.476,0.285,0.662
TimesFM-2.5,AutoTheta,0.95,0.85,1.0,0.388,0.288,0.479
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.44,0.354,0.52
TimesFM-2.5,Naive,1.0,1.0,1.0,0.591,0.512,0.66
TimesFM-2.5,Drift,0.95,0.85,1.0,0.588,0.509,0.663
Toto-1.0,Chronos-2,0.25,0.1,0.45,-0.167,-0.305,-0.06
Toto-1.0,TiRex,0.35,0.15,0.6,-0.008,-0.044,0.03
Toto-1.0,TimesFM-2.5,0.525,0.3,0.725,-0.018,-0.061,0.018
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,TabPFN-TS,0.6,0.4,0.8,-0.061,-0.244,0.087
Toto-1.0,Moirai-2.0,0.675,0.475,0.85,0.022,-0.016,0.061
Toto-1.0,Chronos-Bolt,0.575,0.35,0.775,0.043,-0.009,0.098
Toto-1.0,Sundial-Base,0.75,0.55,0.9,0.086,-0.048,0.191
Toto-1.0,Stat. Ensemble,0.85,0.7,1.0,0.215,0.135,0.297
Toto-1.0,AutoARIMA,0.85,0.7,1.0,0.179,0.122,0.233
Toto-1.0,AutoETS,0.95,0.85,1.0,0.466,0.267,0.659
Toto-1.0,AutoTheta,1.0,1.0,1.0,0.377,0.27,0.474
Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.43,0.339,0.517
Toto-1.0,Naive,1.0,1.0,1.0,0.584,0.501,0.655
Toto-1.0,Drift,1.0,1.0,1.0,0.581,0.501,0.653
TabPFN-TS,Chronos-2,0.15,0.0,0.3,-0.1,-0.188,-0.024
TabPFN-TS,TiRex,0.4,0.2,0.6,0.05,-0.083,0.178
TabPFN-TS,TimesFM-2.5,0.35,0.15,0.6,0.041,-0.101,0.179
TabPFN-TS,Toto-1.0,0.4,0.2,0.6,0.057,-0.096,0.196
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Moirai-2.0,0.65,0.45,0.85,0.079,-0.064,0.204
TabPFN-TS,Chronos-Bolt,0.6,0.4,0.8,0.098,-0.026,0.214
TabPFN-TS,Sundial-Base,0.7,0.45,0.9,0.138,0.011,0.249
TabPFN-TS,Stat. Ensemble,0.7,0.5,0.9,0.26,0.135,0.372
TabPFN-TS,AutoARIMA,0.75,0.55,0.95,0.226,0.114,0.333
TabPFN-TS,AutoETS,0.75,0.55,0.901,0.499,0.281,0.68
TabPFN-TS,AutoTheta,0.95,0.85,1.0,0.413,0.306,0.507
TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.462,0.355,0.55
TabPFN-TS,Naive,1.0,1.0,1.0,0.607,0.512,0.693
TabPFN-TS,Drift,1.0,1.0,1.0,0.605,0.501,0.696
Moirai-2.0,Chronos-2,0.05,0.0,0.15,-0.193,-0.321,-0.09
Moirai-2.0,TiRex,0.25,0.05,0.45,-0.031,-0.066,0.001
Moirai-2.0,TimesFM-2.5,0.375,0.175,0.575,-0.041,-0.106,0.009
Moirai-2.0,Toto-1.0,0.325,0.15,0.525,-0.023,-0.065,0.016
Moirai-2.0,TabPFN-TS,0.35,0.15,0.55,-0.085,-0.256,0.061
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Chronos-Bolt,0.55,0.375,0.725,0.021,-0.019,0.068
Moirai-2.0,Sundial-Base,0.9,0.75,1.0,0.065,-0.067,0.167
Moirai-2.0,Stat. Ensemble,0.8,0.6,0.95,0.197,0.115,0.28
Moirai-2.0,AutoARIMA,0.85,0.7,1.0,0.16,0.099,0.221
Moirai-2.0,AutoETS,0.85,0.7,1.0,0.456,0.251,0.651
Moirai-2.0,AutoTheta,0.9,0.75,1.0,0.363,0.256,0.456
Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.417,0.325,0.5
Moirai-2.0,Naive,0.95,0.85,1.0,0.574,0.481,0.65
Moirai-2.0,Drift,0.95,0.85,1.0,0.571,0.477,0.649
Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.219,-0.342,-0.117
Chronos-Bolt,TiRex,0.1,0.0,0.25,-0.053,-0.093,-0.021
Chronos-Bolt,TimesFM-2.5,0.225,0.05,0.425,-0.064,-0.137,-0.009
Chronos-Bolt,Toto-1.0,0.425,0.225,0.65,-0.045,-0.108,0.009
Chronos-Bolt,TabPFN-TS,0.4,0.2,0.6,-0.109,-0.272,0.025
Chronos-Bolt,Moirai-2.0,0.45,0.275,0.625,-0.022,-0.073,0.019
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,Sundial-Base,0.75,0.55,0.95,0.044,-0.092,0.148
Chronos-Bolt,Stat. Ensemble,0.75,0.55,0.95,0.18,0.111,0.25
Chronos-Bolt,AutoARIMA,0.85,0.7,1.0,0.142,0.097,0.188
Chronos-Bolt,AutoETS,0.75,0.55,0.9,0.443,0.237,0.648
Chronos-Bolt,AutoTheta,0.95,0.85,1.0,0.349,0.248,0.437
Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.404,0.324,0.474
Chronos-Bolt,Naive,0.95,0.85,1.0,0.565,0.479,0.636
Chronos-Bolt,Drift,1.0,1.0,1.0,0.562,0.476,0.639
Sundial-Base,Chronos-2,0.1,0.0,0.25,-0.276,-0.403,-0.161
Sundial-Base,TiRex,0.2,0.05,0.4,-0.102,-0.229,0.027
Sundial-Base,TimesFM-2.5,0.15,0.0,0.3,-0.113,-0.233,0.022
Sundial-Base,Toto-1.0,0.25,0.1,0.45,-0.094,-0.237,0.046
Sundial-Base,TabPFN-TS,0.3,0.1,0.55,-0.16,-0.331,-0.011
Sundial-Base,Moirai-2.0,0.1,0.0,0.25,-0.069,-0.2,0.063
Sundial-Base,Chronos-Bolt,0.25,0.05,0.45,-0.047,-0.174,0.085
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,Stat. Ensemble,0.7,0.5,0.9,0.141,-0.003,0.27
Sundial-Base,AutoARIMA,0.65,0.45,0.85,0.102,-0.03,0.236
Sundial-Base,AutoETS,0.75,0.55,0.9,0.42,0.173,0.64
Sundial-Base,AutoTheta,0.75,0.55,0.9,0.319,0.205,0.422
Sundial-Base,Seasonal Naive,0.95,0.85,1.0,0.376,0.278,0.468
Sundial-Base,Naive,0.95,0.85,1.0,0.544,0.446,0.644
Sundial-Base,Drift,0.9,0.75,1.0,0.541,0.431,0.645
Stat. Ensemble,Chronos-2,0.05,0.0,0.15,-0.486,-0.675,-0.329
Stat. Ensemble,TiRex,0.05,0.0,0.15,-0.284,-0.419,-0.174
Stat. Ensemble,TimesFM-2.5,0.15,0.0,0.3,-0.297,-0.444,-0.177
Stat. Ensemble,Toto-1.0,0.15,0.0,0.3,-0.274,-0.422,-0.157
Stat. Ensemble,TabPFN-TS,0.3,0.1,0.5,-0.352,-0.592,-0.156
Stat. Ensemble,Moirai-2.0,0.2,0.05,0.4,-0.246,-0.388,-0.13
Stat. Ensemble,Chronos-Bolt,0.25,0.05,0.45,-0.219,-0.333,-0.124
Stat. Ensemble,Sundial-Base,0.3,0.1,0.5,-0.165,-0.369,0.003
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoARIMA,0.5,0.3,0.7,-0.046,-0.11,0.011
Stat. Ensemble,AutoETS,0.8,0.65,0.95,0.34,0.109,0.584
Stat. Ensemble,AutoTheta,0.9,0.75,1.0,0.206,0.119,0.291
Stat. Ensemble,Seasonal Naive,0.8,0.625,0.95,0.273,0.165,0.37
Stat. Ensemble,Naive,0.95,0.85,1.0,0.469,0.372,0.556
Stat. Ensemble,Drift,1.0,1.0,1.0,0.466,0.371,0.555
AutoARIMA,Chronos-2,0.05,0.0,0.15,-0.42,-0.589,-0.283
AutoARIMA,TiRex,0.05,0.0,0.15,-0.227,-0.306,-0.164
AutoARIMA,TimesFM-2.5,0.2,0.05,0.351,-0.239,-0.336,-0.155
AutoARIMA,Toto-1.0,0.15,0.0,0.3,-0.218,-0.304,-0.139
AutoARIMA,TabPFN-TS,0.25,0.05,0.45,-0.292,-0.499,-0.129
AutoARIMA,Moirai-2.0,0.15,0.0,0.3,-0.19,-0.283,-0.109
AutoARIMA,Chronos-Bolt,0.15,0.0,0.3,-0.165,-0.231,-0.108
AutoARIMA,Sundial-Base,0.35,0.15,0.55,-0.113,-0.308,0.029
AutoARIMA,Stat. Ensemble,0.5,0.3,0.7,0.044,-0.011,0.099
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,AutoETS,0.75,0.55,0.95,0.36,0.124,0.595
AutoARIMA,AutoTheta,0.8,0.6,0.95,0.241,0.139,0.334
AutoARIMA,Seasonal Naive,0.95,0.875,1.0,0.306,0.199,0.4
AutoARIMA,Naive,0.95,0.85,1.0,0.493,0.39,0.578
AutoARIMA,Drift,0.9,0.75,1.0,0.489,0.393,0.574
AutoETS,Chronos-2,0.05,0.0,0.15,-1.177,-2.364,-0.607
AutoETS,TiRex,0.1,0.0,0.25,-0.888,-1.935,-0.384
AutoETS,TimesFM-2.5,0.1,0.0,0.25,-0.908,-1.961,-0.399
AutoETS,Toto-1.0,0.05,0.0,0.15,-0.874,-1.929,-0.365
AutoETS,TabPFN-TS,0.25,0.099,0.45,-0.995,-2.122,-0.391
AutoETS,Moirai-2.0,0.15,0.0,0.3,-0.84,-1.865,-0.335
AutoETS,Chronos-Bolt,0.25,0.1,0.45,-0.796,-1.839,-0.31
AutoETS,Sundial-Base,0.25,0.1,0.45,-0.725,-1.781,-0.209
AutoETS,Stat. Ensemble,0.2,0.05,0.35,-0.515,-1.402,-0.122
AutoETS,AutoARIMA,0.25,0.05,0.45,-0.564,-1.47,-0.141
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,AutoTheta,0.6,0.4,0.8,-0.216,-0.997,0.152
AutoETS,Seasonal Naive,0.65,0.45,0.85,-0.094,-0.891,0.27
AutoETS,Naive,0.8,0.6,0.95,0.178,-0.412,0.473
AutoETS,Drift,0.9,0.75,1.0,0.171,-0.441,0.461
AutoTheta,Chronos-2,0.0,0.0,0.0,-0.872,-1.19,-0.615
AutoTheta,TiRex,0.0,0.0,0.0,-0.618,-0.87,-0.393
AutoTheta,TimesFM-2.5,0.05,0.0,0.15,-0.634,-0.92,-0.405
AutoTheta,Toto-1.0,0.0,0.0,0.0,-0.605,-0.903,-0.37
AutoTheta,TabPFN-TS,0.05,0.0,0.15,-0.703,-1.03,-0.441
AutoTheta,Moirai-2.0,0.1,0.0,0.25,-0.569,-0.838,-0.344
AutoTheta,Chronos-Bolt,0.05,0.0,0.15,-0.536,-0.778,-0.33
AutoTheta,Sundial-Base,0.25,0.1,0.45,-0.467,-0.731,-0.257
AutoTheta,Stat. Ensemble,0.1,0.0,0.25,-0.26,-0.411,-0.135
AutoTheta,AutoARIMA,0.2,0.05,0.4,-0.318,-0.501,-0.161
AutoTheta,AutoETS,0.4,0.2,0.6,0.178,-0.18,0.499
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,Seasonal Naive,0.8,0.6,0.95,0.085,-0.091,0.214
AutoTheta,Naive,0.85,0.7,1.0,0.332,0.212,0.436
AutoTheta,Drift,0.75,0.55,0.9,0.327,0.202,0.436
Seasonal Naive,Chronos-2,0.0,0.0,0.0,-1.046,-1.382,-0.739
Seasonal Naive,TiRex,0.0,0.0,0.0,-0.767,-1.038,-0.536
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.785,-1.083,-0.548
Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.754,-1.07,-0.513
Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.86,-1.222,-0.549
Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-0.714,-1.001,-0.481
Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.678,-0.902,-0.479
Seasonal Naive,Sundial-Base,0.05,0.0,0.15,-0.603,-0.879,-0.386
Seasonal Naive,Stat. Ensemble,0.2,0.05,0.375,-0.376,-0.587,-0.198
Seasonal Naive,AutoARIMA,0.05,0.0,0.125,-0.44,-0.667,-0.248
Seasonal Naive,AutoETS,0.35,0.15,0.55,0.086,-0.371,0.471
Seasonal Naive,AutoTheta,0.2,0.05,0.4,-0.093,-0.272,0.084
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Naive,0.7,0.525,0.85,0.27,0.133,0.386
Seasonal Naive,Drift,0.75,0.55,0.9,0.265,0.114,0.397
Naive,Chronos-2,0.0,0.0,0.0,-1.801,-2.561,-1.309
Naive,TiRex,0.05,0.0,0.15,-1.42,-1.907,-1.013
Naive,TimesFM-2.5,0.0,0.0,0.0,-1.444,-1.943,-1.05
Naive,Toto-1.0,0.0,0.0,0.0,-1.401,-1.895,-1.005
Naive,TabPFN-TS,0.0,0.0,0.0,-1.547,-2.26,-1.05
Naive,Moirai-2.0,0.05,0.0,0.15,-1.347,-1.858,-0.926
Naive,Chronos-Bolt,0.05,0.0,0.15,-1.297,-1.75,-0.918
Naive,Sundial-Base,0.05,0.0,0.15,-1.195,-1.805,-0.806
Naive,Stat. Ensemble,0.05,0.0,0.15,-0.885,-1.253,-0.593
Naive,AutoARIMA,0.05,0.0,0.15,-0.972,-1.372,-0.64
Naive,AutoETS,0.2,0.05,0.4,-0.217,-0.898,0.292
Naive,AutoTheta,0.15,0.0,0.3,-0.496,-0.774,-0.269
Naive,Seasonal Naive,0.3,0.15,0.475,-0.369,-0.629,-0.153
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Drift,0.85,0.7,1.0,-0.007,-0.056,0.035
Drift,Chronos-2,0.0,0.0,0.0,-1.782,-2.572,-1.273
Drift,TiRex,0.0,0.0,0.0,-1.403,-1.908,-1.003
Drift,TimesFM-2.5,0.05,0.0,0.15,-1.428,-1.966,-1.036
Drift,Toto-1.0,0.0,0.0,0.0,-1.385,-1.884,-1.004
Drift,TabPFN-TS,0.0,0.0,0.0,-1.53,-2.286,-1.004
Drift,Moirai-2.0,0.05,0.0,0.15,-1.332,-1.849,-0.913
Drift,Chronos-Bolt,0.0,0.0,0.0,-1.282,-1.772,-0.909
Drift,Sundial-Base,0.1,0.0,0.25,-1.18,-1.816,-0.759
Drift,Stat. Ensemble,0.0,0.0,0.0,-0.872,-1.247,-0.591
Drift,AutoARIMA,0.1,0.0,0.25,-0.959,-1.348,-0.648
Drift,AutoETS,0.1,0.0,0.25,-0.206,-0.854,0.306
Drift,AutoTheta,0.25,0.1,0.45,-0.486,-0.774,-0.253
Drift,Seasonal Naive,0.25,0.1,0.45,-0.36,-0.657,-0.129
Drift,Naive,0.15,0.0,0.3,0.007,-0.037,0.053
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0