fev-bench / tables /domain_cloud /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
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,Chronos-2,0.65,0.45,0.85,-0.011,-0.063,0.027
Toto-1.0,TimesFM-2.5,0.7,0.5,0.9,0.027,-0.02,0.072
Toto-1.0,TiRex,0.85,0.7,1.0,0.061,0.027,0.114
Toto-1.0,Moirai-2.0,0.95,0.85,1.0,0.098,0.053,0.164
Toto-1.0,Sundial-Base,0.9,0.75,1.0,0.114,0.037,0.182
Toto-1.0,Chronos-Bolt,0.9,0.75,1.0,0.159,0.094,0.224
Toto-1.0,TabPFN-TS,0.85,0.65,1.0,0.15,0.075,0.231
Toto-1.0,Stat. Ensemble,1.0,1.0,1.0,0.352,0.266,0.45
Toto-1.0,AutoARIMA,1.0,1.0,1.0,0.346,0.264,0.448
Toto-1.0,AutoTheta,1.0,1.0,1.0,0.376,0.295,0.468
Toto-1.0,AutoETS,1.0,1.0,1.0,0.361,0.267,0.469
Toto-1.0,Naive,1.0,1.0,1.0,0.537,0.377,0.689
Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.419,0.323,0.529
Toto-1.0,Drift,1.0,1.0,1.0,0.563,0.414,0.702
Chronos-2,Toto-1.0,0.35,0.15,0.55,0.011,-0.028,0.059
Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-2,TimesFM-2.5,0.7,0.5,0.9,0.038,0.009,0.071
Chronos-2,TiRex,0.75,0.55,0.95,0.071,0.022,0.128
Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.108,0.053,0.168
Chronos-2,Sundial-Base,0.9,0.75,1.0,0.123,0.07,0.182
Chronos-2,Chronos-Bolt,0.95,0.85,1.0,0.168,0.101,0.231
Chronos-2,TabPFN-TS,0.9,0.75,1.0,0.159,0.092,0.234
Chronos-2,Stat. Ensemble,1.0,1.0,1.0,0.359,0.272,0.454
Chronos-2,AutoARIMA,1.0,1.0,1.0,0.353,0.266,0.453
Chronos-2,AutoTheta,1.0,1.0,1.0,0.383,0.296,0.47
Chronos-2,AutoETS,1.0,1.0,1.0,0.368,0.281,0.468
Chronos-2,Naive,1.0,1.0,1.0,0.542,0.386,0.689
Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.425,0.331,0.534
Chronos-2,Drift,1.0,1.0,1.0,0.567,0.421,0.704
TimesFM-2.5,Toto-1.0,0.3,0.1,0.5,-0.028,-0.078,0.02
TimesFM-2.5,Chronos-2,0.3,0.1,0.5,-0.039,-0.077,-0.009
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,TiRex,0.65,0.45,0.85,0.035,-0.0,0.077
TimesFM-2.5,Moirai-2.0,0.9,0.75,1.0,0.073,0.035,0.115
TimesFM-2.5,Sundial-Base,0.85,0.7,1.0,0.089,0.041,0.137
TimesFM-2.5,Chronos-Bolt,0.85,0.65,1.0,0.136,0.068,0.199
TimesFM-2.5,TabPFN-TS,0.75,0.55,0.9,0.126,0.059,0.207
TimesFM-2.5,Stat. Ensemble,1.0,1.0,1.0,0.334,0.261,0.415
TimesFM-2.5,AutoARIMA,1.0,1.0,1.0,0.328,0.254,0.415
TimesFM-2.5,AutoTheta,1.0,1.0,1.0,0.359,0.283,0.436
TimesFM-2.5,AutoETS,1.0,1.0,1.0,0.344,0.268,0.433
TimesFM-2.5,Naive,1.0,1.0,1.0,0.524,0.366,0.676
TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.403,0.318,0.501
TimesFM-2.5,Drift,1.0,1.0,1.0,0.55,0.402,0.69
TiRex,Toto-1.0,0.15,0.0,0.3,-0.065,-0.129,-0.028
TiRex,Chronos-2,0.25,0.05,0.45,-0.077,-0.146,-0.022
TiRex,TimesFM-2.5,0.35,0.15,0.55,-0.036,-0.083,0.0
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,Moirai-2.0,0.8,0.6,0.95,0.039,0.014,0.065
TiRex,Sundial-Base,0.85,0.7,1.0,0.056,-0.026,0.115
TiRex,Chronos-Bolt,0.75,0.55,0.9,0.104,0.038,0.166
TiRex,TabPFN-TS,0.7,0.5,0.9,0.095,0.018,0.172
TiRex,Stat. Ensemble,1.0,1.0,1.0,0.31,0.233,0.392
TiRex,AutoARIMA,1.0,1.0,1.0,0.303,0.231,0.382
TiRex,AutoTheta,1.0,1.0,1.0,0.336,0.263,0.412
TiRex,AutoETS,1.0,1.0,1.0,0.32,0.235,0.41
TiRex,Naive,0.95,0.85,1.0,0.507,0.342,0.658
TiRex,Seasonal Naive,1.0,1.0,1.0,0.381,0.295,0.476
TiRex,Drift,1.0,1.0,1.0,0.534,0.385,0.676
Moirai-2.0,Toto-1.0,0.05,0.0,0.15,-0.109,-0.196,-0.056
Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.121,-0.202,-0.056
Moirai-2.0,TimesFM-2.5,0.1,0.0,0.25,-0.078,-0.13,-0.036
Moirai-2.0,TiRex,0.2,0.05,0.4,-0.041,-0.07,-0.015
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Sundial-Base,0.8,0.6,0.95,0.017,-0.056,0.065
Moirai-2.0,Chronos-Bolt,0.65,0.425,0.825,0.068,-0.002,0.135
Moirai-2.0,TabPFN-TS,0.55,0.35,0.75,0.058,-0.02,0.138
Moirai-2.0,Stat. Ensemble,0.95,0.85,1.0,0.282,0.201,0.366
Moirai-2.0,AutoARIMA,0.95,0.85,1.0,0.275,0.203,0.354
Moirai-2.0,AutoTheta,1.0,1.0,1.0,0.309,0.237,0.386
Moirai-2.0,AutoETS,0.95,0.85,1.0,0.292,0.208,0.382
Moirai-2.0,Naive,0.95,0.85,1.0,0.487,0.322,0.638
Moirai-2.0,Seasonal Naive,0.95,0.85,1.0,0.356,0.268,0.451
Moirai-2.0,Drift,1.0,1.0,1.0,0.515,0.369,0.657
Sundial-Base,Toto-1.0,0.1,0.0,0.25,-0.128,-0.223,-0.038
Sundial-Base,Chronos-2,0.1,0.0,0.25,-0.14,-0.222,-0.075
Sundial-Base,TimesFM-2.5,0.15,0.0,0.3,-0.097,-0.159,-0.043
Sundial-Base,TiRex,0.15,0.0,0.3,-0.059,-0.129,0.025
Sundial-Base,Moirai-2.0,0.2,0.05,0.4,-0.018,-0.069,0.053
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,Chronos-Bolt,0.5,0.25,0.7,0.051,-0.023,0.126
Sundial-Base,TabPFN-TS,0.55,0.35,0.75,0.041,-0.034,0.11
Sundial-Base,Stat. Ensemble,0.95,0.85,1.0,0.269,0.182,0.361
Sundial-Base,AutoARIMA,0.95,0.85,1.0,0.262,0.175,0.353
Sundial-Base,AutoTheta,1.0,1.0,1.0,0.296,0.22,0.377
Sundial-Base,AutoETS,0.95,0.85,1.0,0.28,0.184,0.379
Sundial-Base,Naive,1.0,1.0,1.0,0.478,0.322,0.626
Sundial-Base,Seasonal Naive,0.95,0.85,1.0,0.344,0.246,0.453
Sundial-Base,Drift,1.0,1.0,1.0,0.507,0.358,0.646
Chronos-Bolt,Toto-1.0,0.1,0.0,0.25,-0.189,-0.288,-0.104
Chronos-Bolt,Chronos-2,0.05,0.0,0.15,-0.202,-0.3,-0.112
Chronos-Bolt,TimesFM-2.5,0.15,0.0,0.35,-0.157,-0.248,-0.073
Chronos-Bolt,TiRex,0.25,0.1,0.45,-0.116,-0.198,-0.039
Chronos-Bolt,Moirai-2.0,0.35,0.175,0.575,-0.073,-0.156,0.002
Chronos-Bolt,Sundial-Base,0.5,0.3,0.75,-0.054,-0.144,0.022
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,TabPFN-TS,0.5,0.3,0.7,-0.011,-0.128,0.086
Chronos-Bolt,Stat. Ensemble,0.9,0.75,1.0,0.23,0.124,0.336
Chronos-Bolt,AutoARIMA,0.9,0.75,1.0,0.222,0.121,0.337
Chronos-Bolt,AutoTheta,0.95,0.85,1.0,0.258,0.171,0.353
Chronos-Bolt,AutoETS,0.85,0.7,1.0,0.24,0.131,0.358
Chronos-Bolt,Naive,0.95,0.85,1.0,0.449,0.297,0.601
Chronos-Bolt,Seasonal Naive,0.85,0.7,1.0,0.309,0.185,0.434
Chronos-Bolt,Drift,1.0,1.0,1.0,0.48,0.341,0.624
TabPFN-TS,Toto-1.0,0.15,0.0,0.35,-0.176,-0.301,-0.081
TabPFN-TS,Chronos-2,0.1,0.0,0.25,-0.189,-0.305,-0.102
TabPFN-TS,TimesFM-2.5,0.25,0.1,0.45,-0.144,-0.261,-0.063
TabPFN-TS,TiRex,0.3,0.1,0.5,-0.104,-0.208,-0.019
TabPFN-TS,Moirai-2.0,0.45,0.25,0.65,-0.061,-0.161,0.019
TabPFN-TS,Sundial-Base,0.45,0.25,0.65,-0.043,-0.123,0.033
TabPFN-TS,Chronos-Bolt,0.5,0.3,0.7,0.011,-0.095,0.114
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Stat. Ensemble,0.8,0.6,0.95,0.238,0.095,0.36
TabPFN-TS,AutoARIMA,0.8,0.6,0.95,0.231,0.096,0.351
TabPFN-TS,AutoTheta,0.75,0.55,0.95,0.266,0.154,0.375
TabPFN-TS,AutoETS,0.85,0.7,1.0,0.249,0.114,0.367
TabPFN-TS,Naive,0.85,0.65,1.0,0.455,0.285,0.6
TabPFN-TS,Seasonal Naive,0.9,0.75,1.0,0.316,0.178,0.443
TabPFN-TS,Drift,0.95,0.85,1.0,0.485,0.326,0.621
Stat. Ensemble,Toto-1.0,0.0,0.0,0.0,-0.544,-0.817,-0.362
Stat. Ensemble,Chronos-2,0.0,0.0,0.0,-0.561,-0.833,-0.374
Stat. Ensemble,TimesFM-2.5,0.0,0.0,0.0,-0.502,-0.711,-0.353
Stat. Ensemble,TiRex,0.0,0.0,0.0,-0.449,-0.646,-0.304
Stat. Ensemble,Moirai-2.0,0.05,0.0,0.15,-0.393,-0.578,-0.251
Stat. Ensemble,Sundial-Base,0.05,0.0,0.15,-0.369,-0.564,-0.223
Stat. Ensemble,Chronos-Bolt,0.1,0.0,0.25,-0.298,-0.505,-0.141
Stat. Ensemble,TabPFN-TS,0.2,0.05,0.4,-0.312,-0.562,-0.106
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoARIMA,0.475,0.274,0.675,-0.01,-0.058,0.025
Stat. Ensemble,AutoTheta,0.75,0.55,0.95,0.037,-0.013,0.087
Stat. Ensemble,AutoETS,0.775,0.6,0.95,0.014,-0.091,0.087
Stat. Ensemble,Naive,0.75,0.55,0.95,0.285,0.06,0.51
Stat. Ensemble,Seasonal Naive,0.775,0.624,0.925,0.103,-0.009,0.19
Stat. Ensemble,Drift,0.8,0.6,0.95,0.325,0.11,0.536
AutoARIMA,Toto-1.0,0.0,0.0,0.0,-0.529,-0.811,-0.358
AutoARIMA,Chronos-2,0.0,0.0,0.0,-0.546,-0.83,-0.363
AutoARIMA,TimesFM-2.5,0.0,0.0,0.0,-0.487,-0.708,-0.341
AutoARIMA,TiRex,0.0,0.0,0.0,-0.435,-0.619,-0.301
AutoARIMA,Moirai-2.0,0.05,0.0,0.15,-0.379,-0.548,-0.255
AutoARIMA,Sundial-Base,0.05,0.0,0.15,-0.355,-0.545,-0.212
AutoARIMA,Chronos-Bolt,0.1,0.0,0.25,-0.286,-0.508,-0.137
AutoARIMA,TabPFN-TS,0.2,0.05,0.4,-0.3,-0.541,-0.106
AutoARIMA,Stat. Ensemble,0.525,0.325,0.726,0.01,-0.026,0.055
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,AutoTheta,0.6,0.4,0.8,0.046,-0.017,0.107
AutoARIMA,AutoETS,0.725,0.549,0.9,0.024,-0.086,0.103
AutoARIMA,Naive,0.65,0.45,0.85,0.292,0.063,0.513
AutoARIMA,Seasonal Naive,0.825,0.675,0.95,0.112,0.008,0.197
AutoARIMA,Drift,0.8,0.6,0.95,0.331,0.115,0.536
AutoTheta,Toto-1.0,0.0,0.0,0.0,-0.603,-0.881,-0.419
AutoTheta,Chronos-2,0.0,0.0,0.0,-0.621,-0.887,-0.421
AutoTheta,TimesFM-2.5,0.0,0.0,0.0,-0.56,-0.774,-0.394
AutoTheta,TiRex,0.0,0.0,0.0,-0.505,-0.701,-0.356
AutoTheta,Moirai-2.0,0.0,0.0,0.0,-0.446,-0.628,-0.31
AutoTheta,Sundial-Base,0.0,0.0,0.0,-0.421,-0.606,-0.282
AutoTheta,Chronos-Bolt,0.05,0.0,0.15,-0.348,-0.546,-0.206
AutoTheta,TabPFN-TS,0.25,0.05,0.45,-0.363,-0.6,-0.182
AutoTheta,Stat. Ensemble,0.25,0.05,0.45,-0.039,-0.096,0.013
AutoTheta,AutoARIMA,0.4,0.2,0.6,-0.049,-0.12,0.017
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,AutoETS,0.55,0.3,0.75,-0.024,-0.139,0.055
AutoTheta,Naive,0.7,0.5,0.9,0.258,0.05,0.468
AutoTheta,Seasonal Naive,0.8,0.65,0.95,0.068,-0.06,0.171
AutoTheta,Drift,0.85,0.7,1.0,0.299,0.104,0.491
AutoETS,Toto-1.0,0.0,0.0,0.0,-0.566,-0.883,-0.364
AutoETS,Chronos-2,0.0,0.0,0.0,-0.583,-0.881,-0.391
AutoETS,TimesFM-2.5,0.0,0.0,0.0,-0.523,-0.762,-0.366
AutoETS,TiRex,0.0,0.0,0.0,-0.47,-0.695,-0.307
AutoETS,Moirai-2.0,0.05,0.0,0.15,-0.412,-0.619,-0.262
AutoETS,Sundial-Base,0.05,0.0,0.15,-0.388,-0.611,-0.225
AutoETS,Chronos-Bolt,0.15,0.0,0.3,-0.317,-0.559,-0.151
AutoETS,TabPFN-TS,0.15,0.0,0.3,-0.331,-0.581,-0.129
AutoETS,Stat. Ensemble,0.225,0.05,0.4,-0.014,-0.096,0.083
AutoETS,AutoARIMA,0.275,0.1,0.451,-0.024,-0.115,0.079
AutoETS,AutoTheta,0.45,0.25,0.7,0.023,-0.058,0.122
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,Naive,0.55,0.3,0.75,0.275,0.032,0.5
AutoETS,Seasonal Naive,0.725,0.55,0.9,0.09,0.026,0.154
AutoETS,Drift,0.75,0.55,0.9,0.315,0.081,0.528
Naive,Toto-1.0,0.0,0.0,0.0,-1.16,-2.211,-0.604
Naive,Chronos-2,0.0,0.0,0.0,-1.183,-2.214,-0.628
Naive,TimesFM-2.5,0.0,0.0,0.0,-1.101,-2.085,-0.578
Naive,TiRex,0.05,0.0,0.15,-1.027,-1.923,-0.52
Naive,Moirai-2.0,0.05,0.0,0.15,-0.948,-1.762,-0.475
Naive,Sundial-Base,0.0,0.0,0.0,-0.914,-1.673,-0.476
Naive,Chronos-Bolt,0.05,0.0,0.15,-0.816,-1.505,-0.423
Naive,TabPFN-TS,0.15,0.0,0.35,-0.836,-1.501,-0.399
Naive,Stat. Ensemble,0.25,0.05,0.45,-0.399,-1.041,-0.063
Naive,AutoARIMA,0.35,0.15,0.55,-0.413,-1.052,-0.067
Naive,AutoTheta,0.3,0.1,0.5,-0.347,-0.881,-0.053
Naive,AutoETS,0.45,0.25,0.7,-0.379,-1.0,-0.033
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Seasonal Naive,0.6,0.425,0.775,-0.255,-0.874,0.087
Naive,Drift,1.0,1.0,1.0,0.055,0.031,0.085
Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.721,-1.122,-0.477
Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.74,-1.148,-0.496
Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.674,-1.003,-0.466
Seasonal Naive,TiRex,0.0,0.0,0.0,-0.615,-0.909,-0.418
Seasonal Naive,Moirai-2.0,0.05,0.0,0.15,-0.552,-0.822,-0.365
Seasonal Naive,Sundial-Base,0.05,0.0,0.15,-0.525,-0.83,-0.326
Seasonal Naive,Chronos-Bolt,0.15,0.0,0.3,-0.447,-0.766,-0.228
Seasonal Naive,TabPFN-TS,0.1,0.0,0.25,-0.463,-0.796,-0.216
Seasonal Naive,Stat. Ensemble,0.225,0.075,0.376,-0.115,-0.235,0.009
Seasonal Naive,AutoARIMA,0.175,0.05,0.325,-0.126,-0.245,-0.008
Seasonal Naive,AutoTheta,0.2,0.05,0.35,-0.073,-0.206,0.057
Seasonal Naive,AutoETS,0.275,0.1,0.45,-0.099,-0.181,-0.027
Seasonal Naive,Naive,0.4,0.225,0.575,0.203,-0.096,0.466
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Drift,0.6,0.35,0.8,0.247,-0.04,0.497
Drift,Toto-1.0,0.0,0.0,0.0,-1.286,-2.359,-0.705
Drift,Chronos-2,0.0,0.0,0.0,-1.311,-2.381,-0.728
Drift,TimesFM-2.5,0.0,0.0,0.0,-1.224,-2.223,-0.673
Drift,TiRex,0.0,0.0,0.0,-1.146,-2.086,-0.627
Drift,Moirai-2.0,0.0,0.0,0.0,-1.062,-1.913,-0.584
Drift,Sundial-Base,0.0,0.0,0.0,-1.027,-1.828,-0.559
Drift,Chronos-Bolt,0.0,0.0,0.0,-0.922,-1.659,-0.517
Drift,TabPFN-TS,0.05,0.0,0.15,-0.943,-1.639,-0.484
Drift,Stat. Ensemble,0.2,0.05,0.4,-0.481,-1.157,-0.124
Drift,AutoARIMA,0.2,0.05,0.4,-0.495,-1.156,-0.13
Drift,AutoTheta,0.15,0.0,0.3,-0.426,-0.966,-0.116
Drift,AutoETS,0.25,0.1,0.45,-0.46,-1.12,-0.088
Drift,Naive,0.0,0.0,0.0,-0.059,-0.093,-0.032
Drift,Seasonal Naive,0.4,0.2,0.65,-0.329,-0.989,0.038
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0