fev-bench / tables /mini /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,TiRex,0.7,0.5,0.9,0.16,0.056,0.281
Chronos-2,TimesFM-2.5,0.65,0.45,0.85,0.144,0.056,0.239
Chronos-2,Toto-1.0,0.65,0.45,0.85,0.169,0.068,0.279
Chronos-2,TabPFN-TS,0.75,0.55,0.9,0.08,-0.003,0.162
Chronos-2,Moirai-2.0,0.95,0.85,1.0,0.201,0.1,0.304
Chronos-2,Chronos-Bolt,0.95,0.85,1.0,0.22,0.125,0.322
Chronos-2,Sundial-Base,0.95,0.8,1.0,0.268,0.181,0.348
Chronos-2,AutoARIMA,0.9,0.75,1.0,0.355,0.239,0.479
Chronos-2,Stat. Ensemble,0.95,0.85,1.0,0.39,0.277,0.503
Chronos-2,AutoETS,1.0,1.0,1.0,0.563,0.384,0.732
Chronos-2,AutoTheta,1.0,1.0,1.0,0.528,0.423,0.621
Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.572,0.466,0.653
Chronos-2,Naive,1.0,1.0,1.0,0.68,0.599,0.752
Chronos-2,Drift,1.0,1.0,1.0,0.676,0.591,0.751
TiRex,Chronos-2,0.3,0.1,0.5,-0.19,-0.391,-0.06
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,TimesFM-2.5,0.55,0.35,0.75,-0.018,-0.087,0.027
TiRex,Toto-1.0,0.55,0.349,0.75,0.011,-0.027,0.047
TiRex,TabPFN-TS,0.55,0.35,0.75,-0.094,-0.278,0.056
TiRex,Moirai-2.0,0.7,0.5,0.9,0.049,0.006,0.11
TiRex,Chronos-Bolt,0.85,0.7,1.0,0.072,0.015,0.129
TiRex,Sundial-Base,0.8,0.6,0.95,0.129,-0.034,0.265
TiRex,AutoARIMA,0.85,0.7,1.0,0.232,0.148,0.339
TiRex,Stat. Ensemble,0.85,0.7,1.0,0.273,0.162,0.4
TiRex,AutoETS,0.95,0.85,1.0,0.482,0.276,0.68
TiRex,AutoTheta,1.0,1.0,1.0,0.438,0.319,0.55
TiRex,Seasonal Naive,1.0,1.0,1.0,0.491,0.374,0.588
TiRex,Naive,1.0,1.0,1.0,0.619,0.524,0.699
TiRex,Drift,1.0,1.0,1.0,0.615,0.521,0.691
TimesFM-2.5,Chronos-2,0.35,0.15,0.55,-0.169,-0.315,-0.06
TimesFM-2.5,TiRex,0.45,0.25,0.65,0.018,-0.028,0.08
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,Toto-1.0,0.475,0.275,0.7,0.028,-0.02,0.08
TimesFM-2.5,TabPFN-TS,0.6,0.399,0.8,-0.075,-0.25,0.059
TimesFM-2.5,Moirai-2.0,0.675,0.475,0.85,0.066,-0.001,0.134
TimesFM-2.5,Chronos-Bolt,0.825,0.65,0.975,0.088,0.032,0.151
TimesFM-2.5,Sundial-Base,0.85,0.7,1.0,0.145,0.003,0.26
TimesFM-2.5,AutoARIMA,0.8,0.649,0.95,0.246,0.148,0.36
TimesFM-2.5,Stat. Ensemble,0.9,0.75,1.0,0.286,0.17,0.408
TimesFM-2.5,AutoETS,0.9,0.75,1.0,0.492,0.284,0.687
TimesFM-2.5,AutoTheta,0.95,0.85,1.0,0.449,0.323,0.554
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.5,0.386,0.596
TimesFM-2.5,Naive,1.0,1.0,1.0,0.626,0.541,0.697
TimesFM-2.5,Drift,0.95,0.85,1.0,0.622,0.534,0.693
Toto-1.0,Chronos-2,0.35,0.15,0.55,-0.203,-0.388,-0.073
Toto-1.0,TiRex,0.45,0.25,0.651,-0.011,-0.049,0.026
Toto-1.0,TimesFM-2.5,0.525,0.3,0.725,-0.029,-0.087,0.02
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,TabPFN-TS,0.55,0.35,0.75,-0.106,-0.302,0.056
Toto-1.0,Moirai-2.0,0.625,0.4,0.801,0.038,-0.011,0.085
Toto-1.0,Chronos-Bolt,0.575,0.35,0.775,0.062,-0.004,0.131
Toto-1.0,Sundial-Base,0.75,0.55,0.9,0.12,-0.043,0.257
Toto-1.0,AutoARIMA,0.8,0.6,0.95,0.224,0.121,0.342
Toto-1.0,Stat. Ensemble,0.8,0.6,0.95,0.266,0.138,0.404
Toto-1.0,AutoETS,0.95,0.85,1.0,0.477,0.258,0.683
Toto-1.0,AutoTheta,1.0,1.0,1.0,0.432,0.308,0.552
Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.486,0.363,0.591
Toto-1.0,Naive,1.0,1.0,1.0,0.615,0.52,0.694
Toto-1.0,Drift,1.0,1.0,1.0,0.611,0.516,0.689
TabPFN-TS,Chronos-2,0.25,0.1,0.45,-0.088,-0.193,0.003
TabPFN-TS,TiRex,0.45,0.25,0.65,0.086,-0.059,0.218
TabPFN-TS,TimesFM-2.5,0.4,0.2,0.601,0.07,-0.063,0.2
TabPFN-TS,Toto-1.0,0.45,0.25,0.65,0.096,-0.059,0.232
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Moirai-2.0,0.65,0.45,0.85,0.131,-0.008,0.256
TabPFN-TS,Chronos-Bolt,0.65,0.45,0.85,0.152,0.033,0.266
TabPFN-TS,Sundial-Base,0.8,0.6,0.95,0.204,0.086,0.312
TabPFN-TS,AutoARIMA,0.75,0.55,0.901,0.298,0.163,0.427
TabPFN-TS,Stat. Ensemble,0.7,0.5,0.9,0.336,0.202,0.467
TabPFN-TS,AutoETS,0.85,0.7,1.0,0.528,0.318,0.71
TabPFN-TS,AutoTheta,1.0,1.0,1.0,0.487,0.381,0.591
TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.535,0.427,0.629
TabPFN-TS,Naive,1.0,1.0,1.0,0.652,0.568,0.736
TabPFN-TS,Drift,1.0,1.0,1.0,0.648,0.554,0.736
Moirai-2.0,Chronos-2,0.05,0.0,0.15,-0.251,-0.437,-0.111
Moirai-2.0,TiRex,0.3,0.1,0.5,-0.051,-0.124,-0.006
Moirai-2.0,TimesFM-2.5,0.325,0.15,0.525,-0.07,-0.155,0.001
Moirai-2.0,Toto-1.0,0.375,0.199,0.6,-0.04,-0.093,0.011
Moirai-2.0,TabPFN-TS,0.35,0.15,0.55,-0.15,-0.343,0.008
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Chronos-Bolt,0.55,0.375,0.725,0.025,-0.037,0.088
Moirai-2.0,Sundial-Base,0.9,0.75,1.0,0.084,-0.068,0.209
Moirai-2.0,AutoARIMA,0.85,0.7,1.0,0.193,0.069,0.319
Moirai-2.0,Stat. Ensemble,0.8,0.6,0.95,0.236,0.104,0.374
Moirai-2.0,AutoETS,0.9,0.75,1.0,0.458,0.223,0.665
Moirai-2.0,AutoTheta,0.95,0.85,1.0,0.41,0.288,0.527
Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.465,0.355,0.565
Moirai-2.0,Naive,1.0,1.0,1.0,0.6,0.501,0.677
Moirai-2.0,Drift,0.95,0.85,1.0,0.595,0.489,0.678
Chronos-Bolt,Chronos-2,0.05,0.0,0.15,-0.282,-0.474,-0.143
Chronos-Bolt,TiRex,0.15,0.0,0.3,-0.077,-0.148,-0.016
Chronos-Bolt,TimesFM-2.5,0.175,0.025,0.35,-0.097,-0.178,-0.033
Chronos-Bolt,Toto-1.0,0.425,0.225,0.65,-0.066,-0.151,0.004
Chronos-Bolt,TabPFN-TS,0.35,0.15,0.55,-0.179,-0.362,-0.034
Chronos-Bolt,Moirai-2.0,0.45,0.275,0.625,-0.025,-0.096,0.036
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,Sundial-Base,0.7,0.5,0.9,0.061,-0.094,0.187
Chronos-Bolt,AutoARIMA,0.75,0.55,0.901,0.172,0.067,0.289
Chronos-Bolt,Stat. Ensemble,0.8,0.65,0.95,0.217,0.103,0.342
Chronos-Bolt,AutoETS,0.8,0.649,0.95,0.444,0.218,0.665
Chronos-Bolt,AutoTheta,1.0,1.0,1.0,0.395,0.28,0.512
Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.452,0.356,0.542
Chronos-Bolt,Naive,1.0,1.0,1.0,0.59,0.501,0.668
Chronos-Bolt,Drift,1.0,1.0,1.0,0.585,0.495,0.666
Sundial-Base,Chronos-2,0.05,0.0,0.2,-0.366,-0.534,-0.221
Sundial-Base,TiRex,0.2,0.05,0.4,-0.148,-0.361,0.033
Sundial-Base,TimesFM-2.5,0.15,0.0,0.3,-0.169,-0.351,-0.003
Sundial-Base,Toto-1.0,0.25,0.1,0.45,-0.136,-0.346,0.041
Sundial-Base,TabPFN-TS,0.2,0.05,0.4,-0.256,-0.453,-0.094
Sundial-Base,Moirai-2.0,0.1,0.0,0.25,-0.092,-0.264,0.064
Sundial-Base,Chronos-Bolt,0.3,0.1,0.5,-0.066,-0.229,0.086
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,AutoARIMA,0.65,0.45,0.85,0.118,-0.062,0.29
Sundial-Base,Stat. Ensemble,0.6,0.4,0.8,0.166,-0.005,0.329
Sundial-Base,AutoETS,0.7,0.5,0.9,0.41,0.131,0.645
Sundial-Base,AutoTheta,0.75,0.55,0.9,0.355,0.224,0.471
Sundial-Base,Seasonal Naive,0.9,0.75,1.0,0.416,0.303,0.513
Sundial-Base,Naive,0.95,0.85,1.0,0.563,0.462,0.66
Sundial-Base,Drift,0.9,0.75,1.0,0.558,0.442,0.666
AutoARIMA,Chronos-2,0.1,0.0,0.25,-0.55,-0.918,-0.314
AutoARIMA,TiRex,0.15,0.0,0.3,-0.302,-0.512,-0.173
AutoARIMA,TimesFM-2.5,0.2,0.05,0.351,-0.326,-0.562,-0.174
AutoARIMA,Toto-1.0,0.2,0.05,0.4,-0.288,-0.52,-0.138
AutoARIMA,TabPFN-TS,0.25,0.099,0.45,-0.425,-0.746,-0.194
AutoARIMA,Moirai-2.0,0.15,0.0,0.3,-0.239,-0.468,-0.075
AutoARIMA,Chronos-Bolt,0.25,0.099,0.45,-0.208,-0.407,-0.071
AutoARIMA,Sundial-Base,0.35,0.15,0.55,-0.134,-0.409,0.058
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,Stat. Ensemble,0.55,0.325,0.775,0.054,-0.008,0.118
AutoARIMA,AutoETS,0.75,0.55,0.95,0.336,0.112,0.584
AutoARIMA,AutoTheta,0.8,0.6,0.95,0.269,0.156,0.362
AutoARIMA,Seasonal Naive,0.95,0.875,1.0,0.337,0.206,0.439
AutoARIMA,Naive,0.95,0.85,1.0,0.505,0.387,0.593
AutoARIMA,Drift,0.95,0.85,1.0,0.498,0.394,0.581
Stat. Ensemble,Chronos-2,0.05,0.0,0.15,-0.638,-1.011,-0.383
Stat. Ensemble,TiRex,0.15,0.0,0.3,-0.376,-0.668,-0.194
Stat. Ensemble,TimesFM-2.5,0.1,0.0,0.25,-0.401,-0.688,-0.205
Stat. Ensemble,Toto-1.0,0.2,0.05,0.4,-0.362,-0.677,-0.159
Stat. Ensemble,TabPFN-TS,0.3,0.1,0.5,-0.506,-0.876,-0.254
Stat. Ensemble,Moirai-2.0,0.2,0.05,0.4,-0.309,-0.598,-0.115
Stat. Ensemble,Chronos-Bolt,0.2,0.05,0.35,-0.277,-0.519,-0.115
Stat. Ensemble,Sundial-Base,0.4,0.2,0.6,-0.199,-0.491,0.005
Stat. Ensemble,AutoARIMA,0.45,0.225,0.675,-0.057,-0.133,0.008
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoETS,0.8,0.65,0.95,0.309,0.093,0.565
Stat. Ensemble,AutoTheta,0.95,0.85,1.0,0.227,0.137,0.316
Stat. Ensemble,Seasonal Naive,0.85,0.7,0.975,0.3,0.19,0.395
Stat. Ensemble,Naive,0.95,0.85,1.0,0.476,0.373,0.567
Stat. Ensemble,Drift,1.0,1.0,1.0,0.47,0.374,0.556
AutoETS,Chronos-2,0.0,0.0,0.0,-1.289,-2.732,-0.624
AutoETS,TiRex,0.05,0.0,0.15,-0.932,-2.129,-0.381
AutoETS,TimesFM-2.5,0.1,0.0,0.25,-0.968,-2.195,-0.396
AutoETS,Toto-1.0,0.05,0.0,0.15,-0.911,-2.157,-0.347
AutoETS,TabPFN-TS,0.15,0.0,0.3,-1.121,-2.449,-0.466
AutoETS,Moirai-2.0,0.1,0.0,0.25,-0.844,-1.986,-0.288
AutoETS,Chronos-Bolt,0.2,0.05,0.351,-0.797,-1.983,-0.279
AutoETS,Sundial-Base,0.3,0.1,0.5,-0.696,-1.814,-0.151
AutoETS,AutoARIMA,0.25,0.05,0.45,-0.507,-1.405,-0.126
AutoETS,Stat. Ensemble,0.2,0.05,0.35,-0.447,-1.3,-0.103
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,AutoTheta,0.55,0.35,0.75,-0.132,-0.873,0.197
AutoETS,Seasonal Naive,0.6,0.399,0.8,-0.007,-0.774,0.314
AutoETS,Naive,0.8,0.6,0.95,0.225,-0.349,0.489
AutoETS,Drift,0.9,0.75,1.0,0.213,-0.358,0.477
AutoTheta,Chronos-2,0.0,0.0,0.0,-1.12,-1.64,-0.733
AutoTheta,TiRex,0.0,0.0,0.0,-0.781,-1.224,-0.469
AutoTheta,TimesFM-2.5,0.05,0.0,0.15,-0.813,-1.244,-0.477
AutoTheta,Toto-1.0,0.0,0.0,0.0,-0.762,-1.232,-0.445
AutoTheta,TabPFN-TS,0.0,0.0,0.0,-0.949,-1.445,-0.615
AutoTheta,Moirai-2.0,0.05,0.0,0.15,-0.694,-1.113,-0.405
AutoTheta,Chronos-Bolt,0.0,0.0,0.0,-0.653,-1.05,-0.388
AutoTheta,Sundial-Base,0.25,0.1,0.45,-0.551,-0.891,-0.288
AutoTheta,AutoARIMA,0.2,0.05,0.4,-0.368,-0.568,-0.185
AutoTheta,Stat. Ensemble,0.05,0.0,0.15,-0.294,-0.462,-0.159
AutoTheta,AutoETS,0.45,0.25,0.65,0.116,-0.246,0.466
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,Seasonal Naive,0.7,0.5,0.9,0.094,-0.072,0.217
AutoTheta,Naive,0.85,0.7,1.0,0.322,0.188,0.435
AutoTheta,Drift,0.75,0.55,0.9,0.314,0.173,0.433
Seasonal Naive,Chronos-2,0.0,0.0,0.0,-1.338,-1.884,-0.874
Seasonal Naive,TiRex,0.0,0.0,0.0,-0.965,-1.426,-0.596
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-1.001,-1.473,-0.629
Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.944,-1.447,-0.57
Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-1.15,-1.695,-0.745
Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-0.869,-1.298,-0.551
Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.824,-1.184,-0.553
Seasonal Naive,Sundial-Base,0.1,0.0,0.25,-0.711,-1.051,-0.434
Seasonal Naive,AutoARIMA,0.05,0.0,0.125,-0.509,-0.784,-0.26
Seasonal Naive,Stat. Ensemble,0.15,0.025,0.3,-0.428,-0.653,-0.235
Seasonal Naive,AutoETS,0.4,0.2,0.601,0.007,-0.459,0.436
Seasonal Naive,AutoTheta,0.3,0.1,0.5,-0.103,-0.277,0.067
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Naive,0.75,0.6,0.9,0.252,0.104,0.375
Seasonal Naive,Drift,0.8,0.6,0.95,0.243,0.079,0.379
Naive,Chronos-2,0.0,0.0,0.0,-2.128,-3.026,-1.495
Naive,TiRex,0.0,0.0,0.0,-1.628,-2.324,-1.101
Naive,TimesFM-2.5,0.0,0.0,0.0,-1.676,-2.301,-1.181
Naive,Toto-1.0,0.0,0.0,0.0,-1.6,-2.263,-1.082
Naive,TabPFN-TS,0.0,0.0,0.0,-1.876,-2.787,-1.317
Naive,Moirai-2.0,0.0,0.0,0.0,-1.5,-2.099,-1.004
Naive,Chronos-Bolt,0.0,0.0,0.0,-1.439,-2.013,-1.005
Naive,Sundial-Base,0.05,0.0,0.15,-1.289,-1.944,-0.858
Naive,AutoARIMA,0.05,0.0,0.15,-1.018,-1.454,-0.631
Naive,Stat. Ensemble,0.05,0.0,0.15,-0.909,-1.312,-0.594
Naive,AutoETS,0.2,0.05,0.4,-0.29,-0.958,0.259
Naive,AutoTheta,0.15,0.0,0.3,-0.476,-0.769,-0.232
Naive,Seasonal Naive,0.25,0.1,0.4,-0.338,-0.599,-0.116
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Drift,0.85,0.7,1.0,-0.013,-0.074,0.037
Drift,Chronos-2,0.0,0.0,0.0,-2.089,-3.018,-1.445
Drift,TiRex,0.0,0.0,0.0,-1.595,-2.236,-1.088
Drift,TimesFM-2.5,0.05,0.0,0.15,-1.643,-2.256,-1.147
Drift,Toto-1.0,0.0,0.0,0.0,-1.568,-2.216,-1.066
Drift,TabPFN-TS,0.0,0.0,0.0,-1.84,-2.79,-1.244
Drift,Moirai-2.0,0.05,0.0,0.15,-1.469,-2.108,-0.956
Drift,Chronos-Bolt,0.0,0.0,0.0,-1.409,-1.99,-0.979
Drift,Sundial-Base,0.1,0.0,0.25,-1.261,-1.99,-0.791
Drift,AutoARIMA,0.05,0.0,0.15,-0.993,-1.387,-0.651
Drift,Stat. Ensemble,0.0,0.0,0.0,-0.886,-1.253,-0.598
Drift,AutoETS,0.1,0.0,0.25,-0.271,-0.912,0.264
Drift,AutoTheta,0.25,0.1,0.45,-0.457,-0.763,-0.209
Drift,Seasonal Naive,0.2,0.05,0.4,-0.321,-0.61,-0.086
Drift,Naive,0.15,0.0,0.3,0.012,-0.039,0.069
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0