fev-bench / tables /frequency_weekly /pairwise_WQL.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,TimesFM-2.5,0.882,0.706,1.0,0.074,-0.013,0.155
Chronos-2,TiRex,0.765,0.587,0.941,0.09,0.029,0.154
Chronos-2,Chronos-Bolt,0.824,0.647,1.0,0.094,0.007,0.17
Chronos-2,TabPFN-TS,0.588,0.353,0.824,0.032,-0.019,0.085
Chronos-2,Moirai-2.0,0.824,0.647,1.0,0.135,0.041,0.217
Chronos-2,Toto-1.0,0.824,0.647,1.0,0.158,0.087,0.23
Chronos-2,Stat. Ensemble,0.824,0.647,1.0,0.254,0.121,0.374
Chronos-2,Sundial-Base,0.941,0.824,1.0,0.223,0.102,0.311
Chronos-2,AutoARIMA,0.941,0.824,1.0,0.306,0.193,0.402
Chronos-2,AutoETS,0.824,0.647,1.0,0.583,0.277,0.786
Chronos-2,AutoTheta,0.941,0.824,1.0,0.334,0.21,0.443
Chronos-2,Seasonal Naive,0.941,0.824,1.0,0.47,0.339,0.574
Chronos-2,Naive,0.941,0.824,1.0,0.47,0.339,0.574
Chronos-2,Drift,0.941,0.824,1.0,0.471,0.345,0.573
TimesFM-2.5,Chronos-2,0.118,0.0,0.294,-0.08,-0.183,0.013
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,TiRex,0.529,0.294,0.765,0.018,-0.013,0.055
TimesFM-2.5,Chronos-Bolt,0.647,0.441,0.853,0.022,-0.021,0.069
TimesFM-2.5,TabPFN-TS,0.529,0.294,0.765,-0.045,-0.165,0.048
TimesFM-2.5,Moirai-2.0,0.765,0.588,0.941,0.066,0.003,0.129
TimesFM-2.5,Toto-1.0,0.706,0.529,0.941,0.09,0.009,0.166
TimesFM-2.5,Stat. Ensemble,0.824,0.647,1.0,0.194,0.052,0.328
TimesFM-2.5,Sundial-Base,0.882,0.706,1.0,0.16,0.096,0.212
TimesFM-2.5,AutoARIMA,0.882,0.706,1.0,0.25,0.13,0.351
TimesFM-2.5,AutoETS,0.824,0.647,1.0,0.552,0.23,0.773
TimesFM-2.5,AutoTheta,0.941,0.824,1.0,0.281,0.166,0.396
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.427,0.32,0.524
TimesFM-2.5,Naive,1.0,1.0,1.0,0.427,0.32,0.524
TimesFM-2.5,Drift,0.941,0.824,1.0,0.429,0.318,0.531
TiRex,Chronos-2,0.235,0.059,0.413,-0.099,-0.182,-0.03
TiRex,TimesFM-2.5,0.471,0.235,0.706,-0.018,-0.058,0.013
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,Chronos-Bolt,0.765,0.529,0.941,0.004,-0.049,0.05
TiRex,TabPFN-TS,0.529,0.294,0.765,-0.064,-0.173,0.025
TiRex,Moirai-2.0,0.765,0.587,0.941,0.049,-0.016,0.111
TiRex,Toto-1.0,0.882,0.706,1.0,0.074,0.012,0.134
TiRex,Stat. Ensemble,0.765,0.529,0.941,0.18,0.039,0.314
TiRex,Sundial-Base,0.882,0.706,1.0,0.145,0.058,0.21
TiRex,AutoARIMA,0.882,0.706,1.0,0.237,0.118,0.336
TiRex,AutoETS,0.765,0.529,0.941,0.546,0.218,0.771
TiRex,AutoTheta,0.882,0.706,1.0,0.268,0.157,0.384
TiRex,Seasonal Naive,0.941,0.824,1.0,0.417,0.297,0.517
TiRex,Naive,0.941,0.824,1.0,0.417,0.297,0.517
TiRex,Drift,0.882,0.706,1.0,0.418,0.302,0.522
Chronos-Bolt,Chronos-2,0.176,0.0,0.353,-0.104,-0.205,-0.007
Chronos-Bolt,TimesFM-2.5,0.353,0.147,0.559,-0.022,-0.074,0.02
Chronos-Bolt,TiRex,0.235,0.059,0.471,-0.004,-0.052,0.047
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,TabPFN-TS,0.529,0.294,0.765,-0.069,-0.189,0.026
Chronos-Bolt,Moirai-2.0,0.647,0.412,0.853,0.045,-0.019,0.121
Chronos-Bolt,Toto-1.0,0.647,0.412,0.882,0.07,0.004,0.14
Chronos-Bolt,Stat. Ensemble,0.765,0.529,0.941,0.176,0.046,0.302
Chronos-Bolt,Sundial-Base,0.882,0.706,1.0,0.142,0.079,0.197
Chronos-Bolt,AutoARIMA,0.882,0.706,1.0,0.233,0.12,0.33
Chronos-Bolt,AutoETS,0.824,0.647,1.0,0.547,0.218,0.773
Chronos-Bolt,AutoTheta,0.941,0.824,1.0,0.265,0.158,0.37
Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.414,0.309,0.505
Chronos-Bolt,Naive,1.0,1.0,1.0,0.414,0.309,0.505
Chronos-Bolt,Drift,1.0,1.0,1.0,0.416,0.311,0.512
TabPFN-TS,Chronos-2,0.412,0.176,0.647,-0.033,-0.093,0.019
TabPFN-TS,TimesFM-2.5,0.471,0.235,0.706,0.043,-0.05,0.142
TabPFN-TS,TiRex,0.471,0.235,0.706,0.06,-0.026,0.148
TabPFN-TS,Chronos-Bolt,0.471,0.235,0.706,0.064,-0.027,0.159
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Moirai-2.0,0.647,0.412,0.882,0.106,-0.008,0.214
TabPFN-TS,Toto-1.0,0.588,0.353,0.824,0.13,0.035,0.223
TabPFN-TS,Stat. Ensemble,0.706,0.471,0.882,0.229,0.083,0.352
TabPFN-TS,Sundial-Base,0.941,0.824,1.0,0.197,0.086,0.291
TabPFN-TS,AutoARIMA,0.824,0.647,1.0,0.283,0.174,0.367
TabPFN-TS,AutoETS,0.706,0.471,0.882,0.57,0.25,0.783
TabPFN-TS,AutoTheta,0.882,0.706,1.0,0.312,0.194,0.414
TabPFN-TS,Seasonal Naive,0.882,0.706,1.0,0.452,0.325,0.553
TabPFN-TS,Naive,0.882,0.706,1.0,0.452,0.325,0.553
TabPFN-TS,Drift,0.882,0.706,1.0,0.453,0.326,0.558
Moirai-2.0,Chronos-2,0.176,0.0,0.353,-0.156,-0.277,-0.042
Moirai-2.0,TimesFM-2.5,0.235,0.059,0.412,-0.07,-0.148,-0.003
Moirai-2.0,TiRex,0.235,0.059,0.413,-0.051,-0.125,0.016
Moirai-2.0,Chronos-Bolt,0.353,0.147,0.588,-0.047,-0.138,0.018
Moirai-2.0,TabPFN-TS,0.353,0.118,0.588,-0.119,-0.272,0.008
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Toto-1.0,0.647,0.412,0.824,0.026,-0.034,0.083
Moirai-2.0,Stat. Ensemble,0.706,0.471,0.882,0.137,0.008,0.263
Moirai-2.0,Sundial-Base,0.824,0.647,1.0,0.101,-0.014,0.191
Moirai-2.0,AutoARIMA,0.765,0.529,0.941,0.197,0.061,0.317
Moirai-2.0,AutoETS,0.706,0.471,0.882,0.528,0.182,0.766
Moirai-2.0,AutoTheta,0.824,0.647,0.941,0.231,0.116,0.341
Moirai-2.0,Seasonal Naive,0.882,0.706,1.0,0.387,0.259,0.495
Moirai-2.0,Naive,0.882,0.706,1.0,0.387,0.259,0.495
Moirai-2.0,Drift,0.882,0.706,1.0,0.388,0.271,0.491
Toto-1.0,Chronos-2,0.176,0.0,0.353,-0.187,-0.299,-0.095
Toto-1.0,TimesFM-2.5,0.294,0.059,0.471,-0.099,-0.199,-0.009
Toto-1.0,TiRex,0.118,0.0,0.294,-0.08,-0.154,-0.012
Toto-1.0,Chronos-Bolt,0.353,0.118,0.588,-0.075,-0.162,-0.004
Toto-1.0,TabPFN-TS,0.412,0.176,0.647,-0.149,-0.287,-0.036
Toto-1.0,Moirai-2.0,0.353,0.176,0.588,-0.027,-0.091,0.033
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,Stat. Ensemble,0.647,0.412,0.882,0.114,0.007,0.225
Toto-1.0,Sundial-Base,0.765,0.529,0.941,0.077,-0.049,0.18
Toto-1.0,AutoARIMA,0.765,0.529,0.941,0.176,0.076,0.271
Toto-1.0,AutoETS,0.706,0.471,0.882,0.518,0.172,0.758
Toto-1.0,AutoTheta,0.882,0.706,1.0,0.21,0.105,0.308
Toto-1.0,Seasonal Naive,0.941,0.824,1.0,0.37,0.244,0.475
Toto-1.0,Naive,0.941,0.824,1.0,0.37,0.244,0.475
Toto-1.0,Drift,0.941,0.824,1.0,0.372,0.261,0.465
Stat. Ensemble,Chronos-2,0.176,0.0,0.353,-0.34,-0.597,-0.138
Stat. Ensemble,TimesFM-2.5,0.176,0.0,0.353,-0.241,-0.488,-0.055
Stat. Ensemble,TiRex,0.235,0.059,0.471,-0.219,-0.459,-0.041
Stat. Ensemble,Chronos-Bolt,0.235,0.059,0.471,-0.214,-0.433,-0.048
Stat. Ensemble,TabPFN-TS,0.294,0.118,0.529,-0.297,-0.543,-0.09
Stat. Ensemble,Moirai-2.0,0.294,0.118,0.529,-0.159,-0.358,-0.008
Stat. Ensemble,Toto-1.0,0.353,0.118,0.588,-0.129,-0.291,-0.007
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,Sundial-Base,0.412,0.176,0.647,-0.042,-0.256,0.132
Stat. Ensemble,AutoARIMA,0.529,0.294,0.765,0.07,-0.035,0.195
Stat. Ensemble,AutoETS,0.706,0.471,0.884,0.467,0.051,0.734
Stat. Ensemble,AutoTheta,0.882,0.706,1.0,0.108,0.041,0.196
Stat. Ensemble,Seasonal Naive,0.941,0.824,1.0,0.289,0.169,0.395
Stat. Ensemble,Naive,0.941,0.824,1.0,0.289,0.169,0.395
Stat. Ensemble,Drift,0.941,0.824,1.0,0.291,0.192,0.377
Sundial-Base,Chronos-2,0.059,0.0,0.176,-0.286,-0.452,-0.114
Sundial-Base,TimesFM-2.5,0.118,0.0,0.294,-0.191,-0.269,-0.106
Sundial-Base,TiRex,0.118,0.0,0.294,-0.17,-0.266,-0.062
Sundial-Base,Chronos-Bolt,0.118,0.0,0.294,-0.165,-0.245,-0.086
Sundial-Base,TabPFN-TS,0.059,0.0,0.176,-0.245,-0.41,-0.094
Sundial-Base,Moirai-2.0,0.176,0.0,0.353,-0.113,-0.236,0.014
Sundial-Base,Toto-1.0,0.235,0.059,0.471,-0.084,-0.22,0.047
Sundial-Base,Stat. Ensemble,0.588,0.353,0.824,0.04,-0.152,0.204
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,AutoARIMA,0.706,0.471,0.941,0.107,-0.056,0.237
Sundial-Base,AutoETS,0.647,0.412,0.882,0.475,0.09,0.736
Sundial-Base,AutoTheta,0.706,0.471,0.882,0.144,0.008,0.266
Sundial-Base,Seasonal Naive,0.824,0.647,0.943,0.318,0.194,0.423
Sundial-Base,Naive,0.824,0.647,0.943,0.318,0.194,0.423
Sundial-Base,Drift,0.824,0.647,1.0,0.319,0.181,0.442
AutoARIMA,Chronos-2,0.059,0.0,0.176,-0.44,-0.673,-0.239
AutoARIMA,TimesFM-2.5,0.118,0.0,0.294,-0.334,-0.542,-0.149
AutoARIMA,TiRex,0.118,0.0,0.294,-0.31,-0.505,-0.134
AutoARIMA,Chronos-Bolt,0.118,0.0,0.294,-0.304,-0.493,-0.136
AutoARIMA,TabPFN-TS,0.176,0.0,0.353,-0.394,-0.58,-0.21
AutoARIMA,Moirai-2.0,0.235,0.059,0.471,-0.246,-0.465,-0.065
AutoARIMA,Toto-1.0,0.235,0.059,0.471,-0.213,-0.372,-0.082
AutoARIMA,Stat. Ensemble,0.471,0.235,0.706,-0.075,-0.242,0.034
AutoARIMA,Sundial-Base,0.294,0.059,0.529,-0.12,-0.31,0.053
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,AutoETS,0.588,0.353,0.824,0.42,-0.002,0.715
AutoARIMA,AutoTheta,0.706,0.471,0.882,0.041,-0.062,0.118
AutoARIMA,Seasonal Naive,0.882,0.706,1.0,0.236,0.096,0.346
AutoARIMA,Naive,0.882,0.706,1.0,0.236,0.096,0.346
AutoARIMA,Drift,0.882,0.706,1.0,0.238,0.1,0.354
AutoETS,Chronos-2,0.176,0.0,0.353,-1.4,-3.668,-0.383
AutoETS,TimesFM-2.5,0.176,0.0,0.353,-1.233,-3.406,-0.299
AutoETS,TiRex,0.235,0.059,0.471,-1.201,-3.366,-0.279
AutoETS,Chronos-Bolt,0.176,0.0,0.353,-1.206,-3.408,-0.279
AutoETS,TabPFN-TS,0.294,0.118,0.529,-1.326,-3.6,-0.333
AutoETS,Moirai-2.0,0.294,0.118,0.529,-1.121,-3.271,-0.223
AutoETS,Toto-1.0,0.294,0.118,0.529,-1.074,-3.125,-0.207
AutoETS,Stat. Ensemble,0.294,0.116,0.529,-0.877,-2.759,-0.053
AutoETS,Sundial-Base,0.353,0.118,0.588,-0.903,-2.791,-0.099
AutoETS,AutoARIMA,0.412,0.176,0.647,-0.724,-2.513,0.002
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,AutoTheta,0.529,0.294,0.765,-0.694,-2.439,0.032
AutoETS,Seasonal Naive,0.706,0.529,0.882,-0.385,-1.856,0.2
AutoETS,Naive,0.706,0.529,0.882,-0.385,-1.856,0.2
AutoETS,Drift,0.765,0.529,0.941,-0.39,-1.866,0.187
AutoTheta,Chronos-2,0.059,0.0,0.176,-0.503,-0.796,-0.266
AutoTheta,TimesFM-2.5,0.059,0.0,0.176,-0.391,-0.657,-0.2
AutoTheta,TiRex,0.118,0.0,0.294,-0.367,-0.624,-0.186
AutoTheta,Chronos-Bolt,0.059,0.0,0.176,-0.361,-0.587,-0.187
AutoTheta,TabPFN-TS,0.118,0.0,0.294,-0.454,-0.706,-0.24
AutoTheta,Moirai-2.0,0.176,0.059,0.353,-0.3,-0.517,-0.131
AutoTheta,Toto-1.0,0.118,0.0,0.294,-0.266,-0.446,-0.117
AutoTheta,Stat. Ensemble,0.118,0.0,0.294,-0.121,-0.244,-0.043
AutoTheta,Sundial-Base,0.294,0.118,0.529,-0.168,-0.362,-0.008
AutoTheta,AutoARIMA,0.294,0.118,0.529,-0.043,-0.134,0.059
AutoTheta,AutoETS,0.471,0.235,0.706,0.41,-0.033,0.709
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,Seasonal Naive,0.765,0.529,0.941,0.203,0.105,0.29
AutoTheta,Naive,0.765,0.529,0.941,0.203,0.105,0.29
AutoTheta,Drift,0.706,0.471,0.882,0.205,0.11,0.297
Seasonal Naive,Chronos-2,0.059,0.0,0.176,-0.885,-1.345,-0.512
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.745,-1.103,-0.471
Seasonal Naive,TiRex,0.059,0.0,0.176,-0.715,-1.069,-0.423
Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.707,-1.02,-0.448
Seasonal Naive,TabPFN-TS,0.118,0.0,0.294,-0.825,-1.236,-0.481
Seasonal Naive,Moirai-2.0,0.118,0.0,0.294,-0.631,-0.979,-0.35
Seasonal Naive,Toto-1.0,0.059,0.0,0.176,-0.588,-0.905,-0.322
Seasonal Naive,Stat. Ensemble,0.059,0.0,0.176,-0.407,-0.653,-0.204
Seasonal Naive,Sundial-Base,0.176,0.057,0.353,-0.465,-0.735,-0.241
Seasonal Naive,AutoARIMA,0.118,0.0,0.294,-0.309,-0.53,-0.106
Seasonal Naive,AutoETS,0.294,0.118,0.471,0.278,-0.25,0.65
Seasonal Naive,AutoTheta,0.235,0.059,0.471,-0.255,-0.407,-0.117
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Drift,0.824,0.647,1.0,0.003,-0.067,0.061
Naive,Chronos-2,0.059,0.0,0.176,-0.885,-1.345,-0.512
Naive,TimesFM-2.5,0.0,0.0,0.0,-0.745,-1.103,-0.471
Naive,TiRex,0.059,0.0,0.176,-0.715,-1.069,-0.423
Naive,Chronos-Bolt,0.0,0.0,0.0,-0.707,-1.02,-0.448
Naive,TabPFN-TS,0.118,0.0,0.294,-0.825,-1.236,-0.481
Naive,Moirai-2.0,0.118,0.0,0.294,-0.631,-0.979,-0.35
Naive,Toto-1.0,0.059,0.0,0.176,-0.588,-0.905,-0.322
Naive,Stat. Ensemble,0.059,0.0,0.176,-0.407,-0.653,-0.204
Naive,Sundial-Base,0.176,0.057,0.353,-0.465,-0.735,-0.241
Naive,AutoARIMA,0.118,0.0,0.294,-0.309,-0.53,-0.106
Naive,AutoETS,0.294,0.118,0.471,0.278,-0.25,0.65
Naive,AutoTheta,0.235,0.059,0.471,-0.255,-0.407,-0.117
Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Drift,0.824,0.647,1.0,0.003,-0.067,0.061
Drift,Chronos-2,0.059,0.0,0.176,-0.89,-1.34,-0.527
Drift,TimesFM-2.5,0.059,0.0,0.176,-0.75,-1.131,-0.465
Drift,TiRex,0.118,0.0,0.294,-0.719,-1.091,-0.433
Drift,Chronos-Bolt,0.0,0.0,0.0,-0.711,-1.05,-0.451
Drift,TabPFN-TS,0.118,0.0,0.294,-0.829,-1.263,-0.484
Drift,Moirai-2.0,0.118,0.0,0.294,-0.635,-0.965,-0.372
Drift,Toto-1.0,0.059,0.0,0.176,-0.592,-0.871,-0.352
Drift,Stat. Ensemble,0.059,0.0,0.176,-0.41,-0.606,-0.237
Drift,Sundial-Base,0.176,0.0,0.353,-0.469,-0.793,-0.221
Drift,AutoARIMA,0.118,0.0,0.294,-0.312,-0.548,-0.111
Drift,AutoETS,0.235,0.059,0.471,0.28,-0.23,0.651
Drift,AutoTheta,0.294,0.118,0.529,-0.258,-0.422,-0.124
Drift,Seasonal Naive,0.176,0.0,0.353,-0.003,-0.065,0.063
Drift,Naive,0.176,0.0,0.353,-0.003,-0.065,0.063
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0