fev-bench / tables /mini /pairwise_MASE.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,0.75,0.55,0.95,0.131,0.053,0.212
Chronos-2,TimesFM-2.5,0.8,0.6,0.95,0.118,0.039,0.207
Chronos-2,Toto-1.0,0.7,0.5,0.9,0.137,0.052,0.225
Chronos-2,TabPFN-TS,0.8,0.649,0.95,0.081,0.012,0.148
Chronos-2,Moirai-2.0,0.9,0.75,1.0,0.147,0.07,0.228
Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.167,0.095,0.241
Chronos-2,Sundial-Base,0.85,0.7,1.0,0.15,0.066,0.228
Chronos-2,Stat. Ensemble,0.85,0.7,1.0,0.244,0.156,0.333
Chronos-2,AutoARIMA,0.95,0.85,1.0,0.251,0.169,0.33
Chronos-2,AutoTheta,0.95,0.85,1.0,0.3,0.213,0.381
Chronos-2,AutoETS,0.95,0.85,1.0,0.389,0.257,0.524
Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.404,0.32,0.476
Chronos-2,Naive,1.0,1.0,1.0,0.492,0.389,0.595
Chronos-2,Drift,0.95,0.85,1.0,0.491,0.387,0.599
TiRex,Chronos-2,0.25,0.05,0.45,-0.15,-0.269,-0.056
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,TimesFM-2.5,0.55,0.35,0.75,-0.014,-0.062,0.022
TiRex,Toto-1.0,0.65,0.45,0.85,0.007,-0.025,0.037
TiRex,TabPFN-TS,0.6,0.4,0.8,-0.057,-0.225,0.074
TiRex,Moirai-2.0,0.65,0.45,0.85,0.019,-0.006,0.046
TiRex,Chronos-Bolt,0.85,0.7,1.0,0.041,0.01,0.074
TiRex,Sundial-Base,0.6,0.4,0.8,0.022,-0.117,0.12
TiRex,Stat. Ensemble,0.8,0.65,0.95,0.13,0.072,0.208
TiRex,AutoARIMA,0.8,0.6,0.95,0.138,0.09,0.191
TiRex,AutoTheta,1.0,1.0,1.0,0.195,0.12,0.277
TiRex,AutoETS,0.9,0.75,1.0,0.298,0.156,0.442
TiRex,Seasonal Naive,0.95,0.85,1.0,0.314,0.237,0.395
TiRex,Naive,0.95,0.85,1.0,0.415,0.317,0.505
TiRex,Drift,0.95,0.85,1.0,0.414,0.326,0.502
TimesFM-2.5,Chronos-2,0.2,0.05,0.4,-0.134,-0.261,-0.041
TimesFM-2.5,TiRex,0.45,0.25,0.65,0.014,-0.022,0.058
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,Toto-1.0,0.475,0.275,0.7,0.02,-0.008,0.053
TimesFM-2.5,TabPFN-TS,0.6,0.35,0.8,-0.043,-0.219,0.093
TimesFM-2.5,Moirai-2.0,0.675,0.475,0.85,0.033,-0.006,0.073
TimesFM-2.5,Chronos-Bolt,0.725,0.525,0.9,0.055,0.011,0.104
TimesFM-2.5,Sundial-Base,0.75,0.55,0.9,0.036,-0.106,0.138
TimesFM-2.5,Stat. Ensemble,0.85,0.7,1.0,0.142,0.08,0.218
TimesFM-2.5,AutoARIMA,0.85,0.7,1.0,0.15,0.096,0.208
TimesFM-2.5,AutoTheta,0.95,0.85,1.0,0.206,0.122,0.3
TimesFM-2.5,AutoETS,0.85,0.7,1.0,0.307,0.168,0.445
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.323,0.242,0.409
TimesFM-2.5,Naive,1.0,1.0,1.0,0.424,0.335,0.513
TimesFM-2.5,Drift,0.95,0.85,1.0,0.423,0.334,0.508
Toto-1.0,Chronos-2,0.3,0.1,0.5,-0.158,-0.29,-0.054
Toto-1.0,TiRex,0.35,0.15,0.55,-0.007,-0.039,0.024
Toto-1.0,TimesFM-2.5,0.525,0.3,0.725,-0.021,-0.056,0.008
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,-0.064,-0.239,0.077
Toto-1.0,Moirai-2.0,0.675,0.475,0.85,0.012,-0.023,0.044
Toto-1.0,Chronos-Bolt,0.675,0.475,0.85,0.035,-0.01,0.085
Toto-1.0,Sundial-Base,0.6,0.4,0.8,0.015,-0.124,0.125
Toto-1.0,Stat. Ensemble,0.8,0.6,0.95,0.125,0.057,0.207
Toto-1.0,AutoARIMA,0.85,0.7,1.0,0.132,0.079,0.187
Toto-1.0,AutoTheta,0.9,0.75,1.0,0.189,0.104,0.29
Toto-1.0,AutoETS,0.9,0.75,1.0,0.293,0.148,0.438
Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.309,0.226,0.399
Toto-1.0,Naive,1.0,1.0,1.0,0.411,0.314,0.507
Toto-1.0,Drift,0.95,0.85,1.0,0.411,0.321,0.501
TabPFN-TS,Chronos-2,0.2,0.05,0.351,-0.088,-0.174,-0.012
TabPFN-TS,TiRex,0.4,0.2,0.6,0.054,-0.08,0.184
TabPFN-TS,TimesFM-2.5,0.4,0.2,0.65,0.041,-0.103,0.179
TabPFN-TS,Toto-1.0,0.4,0.2,0.6,0.06,-0.083,0.193
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Moirai-2.0,0.65,0.45,0.85,0.072,-0.064,0.201
TabPFN-TS,Chronos-Bolt,0.55,0.349,0.8,0.093,-0.027,0.214
TabPFN-TS,Sundial-Base,0.55,0.3,0.75,0.075,-0.054,0.19
TabPFN-TS,Stat. Ensemble,0.65,0.45,0.85,0.177,0.049,0.304
TabPFN-TS,AutoARIMA,0.75,0.55,0.9,0.185,0.068,0.296
TabPFN-TS,AutoTheta,0.8,0.6,0.95,0.238,0.125,0.347
TabPFN-TS,AutoETS,0.75,0.55,0.95,0.336,0.149,0.489
TabPFN-TS,Seasonal Naive,0.95,0.85,1.0,0.351,0.263,0.435
TabPFN-TS,Naive,0.95,0.85,1.0,0.447,0.327,0.56
TabPFN-TS,Drift,0.9,0.75,1.0,0.446,0.321,0.564
Moirai-2.0,Chronos-2,0.1,0.0,0.25,-0.172,-0.296,-0.075
Moirai-2.0,TiRex,0.35,0.15,0.55,-0.019,-0.049,0.006
Moirai-2.0,TimesFM-2.5,0.325,0.15,0.525,-0.034,-0.078,0.006
Moirai-2.0,Toto-1.0,0.325,0.15,0.525,-0.012,-0.046,0.023
Moirai-2.0,TabPFN-TS,0.35,0.15,0.55,-0.078,-0.252,0.06
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Chronos-Bolt,0.55,0.375,0.725,0.023,-0.016,0.067
Moirai-2.0,Sundial-Base,0.55,0.35,0.75,0.003,-0.129,0.111
Moirai-2.0,Stat. Ensemble,0.85,0.7,1.0,0.114,0.044,0.201
Moirai-2.0,AutoARIMA,0.8,0.6,0.95,0.122,0.058,0.186
Moirai-2.0,AutoTheta,0.9,0.75,1.0,0.179,0.096,0.273
Moirai-2.0,AutoETS,0.8,0.65,0.95,0.284,0.138,0.433
Moirai-2.0,Seasonal Naive,0.95,0.85,1.0,0.301,0.218,0.39
Moirai-2.0,Naive,0.95,0.85,1.0,0.404,0.3,0.498
Moirai-2.0,Drift,0.9,0.75,1.0,0.403,0.302,0.499
Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.2,-0.317,-0.105
Chronos-Bolt,TiRex,0.15,0.0,0.3,-0.043,-0.08,-0.01
Chronos-Bolt,TimesFM-2.5,0.275,0.1,0.475,-0.058,-0.116,-0.011
Chronos-Bolt,Toto-1.0,0.325,0.15,0.525,-0.036,-0.093,0.01
Chronos-Bolt,TabPFN-TS,0.45,0.2,0.651,-0.103,-0.273,0.026
Chronos-Bolt,Moirai-2.0,0.45,0.275,0.625,-0.023,-0.072,0.015
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,Sundial-Base,0.5,0.3,0.7,-0.02,-0.16,0.079
Chronos-Bolt,Stat. Ensemble,0.8,0.65,0.95,0.093,0.041,0.153
Chronos-Bolt,AutoARIMA,0.8,0.65,0.95,0.101,0.053,0.152
Chronos-Bolt,AutoTheta,0.95,0.85,1.0,0.16,0.103,0.229
Chronos-Bolt,AutoETS,0.8,0.65,0.95,0.267,0.12,0.42
Chronos-Bolt,Seasonal Naive,0.95,0.85,1.0,0.284,0.225,0.352
Chronos-Bolt,Naive,0.95,0.85,1.0,0.39,0.293,0.482
Chronos-Bolt,Drift,0.95,0.85,1.0,0.389,0.3,0.484
Sundial-Base,Chronos-2,0.15,0.0,0.3,-0.176,-0.296,-0.07
Sundial-Base,TiRex,0.4,0.2,0.6,-0.022,-0.136,0.105
Sundial-Base,TimesFM-2.5,0.25,0.1,0.45,-0.037,-0.16,0.096
Sundial-Base,Toto-1.0,0.4,0.2,0.6,-0.016,-0.142,0.11
Sundial-Base,TabPFN-TS,0.45,0.25,0.7,-0.081,-0.235,0.051
Sundial-Base,Moirai-2.0,0.45,0.25,0.65,-0.003,-0.125,0.114
Sundial-Base,Chronos-Bolt,0.5,0.3,0.7,0.02,-0.085,0.138
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,Stat. Ensemble,0.65,0.45,0.85,0.111,-0.023,0.246
Sundial-Base,AutoARIMA,0.65,0.45,0.85,0.119,-0.012,0.256
Sundial-Base,AutoTheta,0.85,0.7,1.0,0.177,0.08,0.288
Sundial-Base,AutoETS,0.7,0.5,0.9,0.282,0.087,0.452
Sundial-Base,Seasonal Naive,0.9,0.75,1.0,0.298,0.209,0.391
Sundial-Base,Naive,0.95,0.85,1.0,0.402,0.297,0.533
Sundial-Base,Drift,0.9,0.75,1.0,0.401,0.276,0.545
Stat. Ensemble,Chronos-2,0.15,0.0,0.3,-0.323,-0.499,-0.185
Stat. Ensemble,TiRex,0.2,0.05,0.35,-0.15,-0.262,-0.077
Stat. Ensemble,TimesFM-2.5,0.15,0.0,0.3,-0.166,-0.28,-0.087
Stat. Ensemble,Toto-1.0,0.2,0.05,0.4,-0.142,-0.261,-0.061
Stat. Ensemble,TabPFN-TS,0.35,0.15,0.55,-0.216,-0.437,-0.051
Stat. Ensemble,Moirai-2.0,0.15,0.0,0.3,-0.128,-0.251,-0.046
Stat. Ensemble,Chronos-Bolt,0.2,0.05,0.35,-0.102,-0.18,-0.043
Stat. Ensemble,Sundial-Base,0.35,0.15,0.55,-0.125,-0.327,0.022
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoARIMA,0.6,0.4,0.776,0.009,-0.04,0.05
Stat. Ensemble,AutoTheta,0.85,0.7,1.0,0.074,-0.0,0.155
Stat. Ensemble,AutoETS,0.8,0.65,0.95,0.192,0.055,0.351
Stat. Ensemble,Seasonal Naive,0.9,0.775,1.0,0.211,0.122,0.301
Stat. Ensemble,Naive,0.9,0.75,1.0,0.328,0.221,0.426
Stat. Ensemble,Drift,0.95,0.85,1.0,0.327,0.232,0.422
AutoARIMA,Chronos-2,0.05,0.0,0.15,-0.335,-0.493,-0.204
AutoARIMA,TiRex,0.2,0.05,0.4,-0.16,-0.237,-0.099
AutoARIMA,TimesFM-2.5,0.15,0.0,0.3,-0.177,-0.263,-0.106
AutoARIMA,Toto-1.0,0.15,0.0,0.3,-0.153,-0.23,-0.086
AutoARIMA,TabPFN-TS,0.25,0.1,0.45,-0.227,-0.42,-0.072
AutoARIMA,Moirai-2.0,0.2,0.05,0.4,-0.138,-0.228,-0.061
AutoARIMA,Chronos-Bolt,0.2,0.05,0.35,-0.112,-0.179,-0.056
AutoARIMA,Sundial-Base,0.35,0.15,0.55,-0.135,-0.345,0.012
AutoARIMA,Stat. Ensemble,0.4,0.224,0.6,-0.009,-0.053,0.039
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,AutoTheta,0.5,0.3,0.7,0.066,-0.014,0.158
AutoARIMA,AutoETS,0.65,0.45,0.85,0.185,0.034,0.342
AutoARIMA,Seasonal Naive,0.9,0.775,1.0,0.204,0.115,0.294
AutoARIMA,Naive,0.9,0.75,1.0,0.322,0.212,0.425
AutoARIMA,Drift,0.9,0.75,1.0,0.321,0.227,0.417
AutoTheta,Chronos-2,0.05,0.0,0.15,-0.429,-0.615,-0.27
AutoTheta,TiRex,0.0,0.0,0.0,-0.242,-0.384,-0.137
AutoTheta,TimesFM-2.5,0.05,0.0,0.15,-0.259,-0.429,-0.138
AutoTheta,Toto-1.0,0.1,0.0,0.25,-0.234,-0.409,-0.117
AutoTheta,TabPFN-TS,0.2,0.05,0.4,-0.313,-0.532,-0.143
AutoTheta,Moirai-2.0,0.1,0.0,0.25,-0.218,-0.376,-0.106
AutoTheta,Chronos-Bolt,0.05,0.0,0.15,-0.191,-0.297,-0.115
AutoTheta,Sundial-Base,0.15,0.0,0.3,-0.215,-0.405,-0.086
AutoTheta,Stat. Ensemble,0.15,0.0,0.3,-0.08,-0.183,0.0
AutoTheta,AutoARIMA,0.5,0.3,0.7,-0.07,-0.188,0.013
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,AutoETS,0.55,0.35,0.75,0.128,-0.064,0.315
AutoTheta,Seasonal Naive,0.95,0.85,1.0,0.148,0.088,0.2
AutoTheta,Naive,0.95,0.85,1.0,0.274,0.184,0.368
AutoTheta,Drift,0.85,0.7,1.0,0.273,0.182,0.37
AutoETS,Chronos-2,0.05,0.0,0.15,-0.638,-1.102,-0.346
AutoETS,TiRex,0.1,0.0,0.25,-0.424,-0.791,-0.184
AutoETS,TimesFM-2.5,0.15,0.0,0.3,-0.444,-0.803,-0.203
AutoETS,Toto-1.0,0.1,0.0,0.25,-0.414,-0.78,-0.173
AutoETS,TabPFN-TS,0.25,0.05,0.45,-0.505,-0.957,-0.175
AutoETS,Moirai-2.0,0.2,0.05,0.35,-0.397,-0.764,-0.16
AutoETS,Chronos-Bolt,0.2,0.05,0.35,-0.365,-0.725,-0.136
AutoETS,Sundial-Base,0.3,0.1,0.5,-0.393,-0.824,-0.095
AutoETS,Stat. Ensemble,0.2,0.05,0.35,-0.238,-0.54,-0.059
AutoETS,AutoARIMA,0.35,0.15,0.55,-0.227,-0.519,-0.035
AutoETS,AutoTheta,0.45,0.25,0.65,-0.147,-0.46,0.06
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,Seasonal Naive,0.7,0.5,0.9,0.023,-0.279,0.233
AutoETS,Naive,0.7,0.5,0.9,0.168,-0.073,0.351
AutoETS,Drift,0.7,0.5,0.9,0.166,-0.056,0.342
Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.677,-0.909,-0.471
Seasonal Naive,TiRex,0.05,0.0,0.15,-0.457,-0.653,-0.311
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.478,-0.692,-0.32
Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.448,-0.665,-0.292
Seasonal Naive,TabPFN-TS,0.05,0.0,0.15,-0.541,-0.77,-0.357
Seasonal Naive,Moirai-2.0,0.05,0.0,0.15,-0.43,-0.64,-0.278
Seasonal Naive,Chronos-Bolt,0.05,0.0,0.15,-0.397,-0.544,-0.29
Seasonal Naive,Sundial-Base,0.1,0.0,0.25,-0.425,-0.642,-0.265
Seasonal Naive,Stat. Ensemble,0.1,0.0,0.225,-0.267,-0.431,-0.139
Seasonal Naive,AutoARIMA,0.1,0.0,0.225,-0.256,-0.417,-0.13
Seasonal Naive,AutoTheta,0.05,0.0,0.15,-0.174,-0.25,-0.096
Seasonal Naive,AutoETS,0.3,0.1,0.5,-0.024,-0.304,0.218
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Naive,0.6,0.4,0.775,0.148,0.005,0.284
Seasonal Naive,Drift,0.65,0.45,0.85,0.147,0.006,0.293
Naive,Chronos-2,0.0,0.0,0.0,-0.968,-1.469,-0.636
Naive,TiRex,0.05,0.0,0.15,-0.71,-1.022,-0.464
Naive,TimesFM-2.5,0.0,0.0,0.0,-0.735,-1.055,-0.504
Naive,Toto-1.0,0.0,0.0,0.0,-0.699,-1.028,-0.458
Naive,TabPFN-TS,0.05,0.0,0.15,-0.809,-1.274,-0.485
Naive,Moirai-2.0,0.05,0.0,0.15,-0.678,-0.994,-0.428
Naive,Chronos-Bolt,0.05,0.0,0.15,-0.64,-0.931,-0.415
Naive,Sundial-Base,0.05,0.0,0.15,-0.673,-1.142,-0.422
Naive,Stat. Ensemble,0.1,0.0,0.25,-0.488,-0.741,-0.284
Naive,AutoARIMA,0.1,0.0,0.25,-0.474,-0.74,-0.269
Naive,AutoTheta,0.05,0.0,0.15,-0.377,-0.582,-0.225
Naive,AutoETS,0.3,0.1,0.5,-0.201,-0.54,0.068
Naive,Seasonal Naive,0.4,0.225,0.6,-0.174,-0.396,-0.005
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Drift,0.75,0.55,0.9,-0.002,-0.052,0.045
Drift,Chronos-2,0.05,0.0,0.15,-0.965,-1.493,-0.631
Drift,TiRex,0.05,0.0,0.15,-0.708,-1.01,-0.484
Drift,TimesFM-2.5,0.05,0.0,0.15,-0.732,-1.033,-0.5
Drift,Toto-1.0,0.05,0.0,0.15,-0.697,-1.005,-0.474
Drift,TabPFN-TS,0.1,0.0,0.25,-0.806,-1.295,-0.473
Drift,Moirai-2.0,0.1,0.0,0.25,-0.676,-0.994,-0.432
Drift,Chronos-Bolt,0.05,0.0,0.15,-0.637,-0.937,-0.428
Drift,Sundial-Base,0.1,0.0,0.25,-0.671,-1.196,-0.381
Drift,Stat. Ensemble,0.05,0.0,0.15,-0.485,-0.731,-0.303
Drift,AutoARIMA,0.1,0.0,0.25,-0.472,-0.715,-0.294
Drift,AutoTheta,0.15,0.0,0.3,-0.375,-0.588,-0.223
Drift,AutoETS,0.3,0.1,0.5,-0.2,-0.519,0.053
Drift,Seasonal Naive,0.35,0.15,0.55,-0.172,-0.415,-0.006
Drift,Naive,0.25,0.1,0.45,0.002,-0.047,0.05
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0