fev-bench / tables /frequency_sub_hourly /leaderboard_SQL.csv
shchuro's picture
Update results
86cf9ec
model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
Chronos-2,93.75,56.381305085766286,0.0,1.219865412061035,0.0,0.0
Toto-1.0,88.75,54.0349203442283,0.0,53.08930704428572,0.041666666666666664,0.0
TimesFM-2.5,83.33333333333334,53.090548120238765,0.0,8.086343701896517,0.041666666666666664,0.0
TiRex,82.5,52.710892944466025,0.0,0.534368017900975,0.041666666666666664,0.0
Moirai-2.0,71.35416666666667,50.17769220777839,0.0,1.7491858470238095,0.25,0.0
FlowState,70.20833333333333,47.894556376520924,0.0,10.897278185476189,0.041666666666666664,0.0
TFT,65.20833333333333,48.04926998698471,1154.7495615716732,1.2445208104761905,0.0,0.0
PatchTST,63.22916666666668,47.5861909531335,1257.4287658338405,2.5367794131867605,0.0,0.0
Chronos-Bolt,60.312500000000014,46.3687172213469,0.0,0.5042001652436238,0.0,0.0
TabPFN-TS,60.00000000000001,47.148822968097335,0.0,300.46992049143205,0.0,0.0
Sundial-Base,57.49999999999999,46.75728672813329,0.0,7.915062387440475,0.041666666666666664,0.0
DeepAR,53.22916666666667,42.297561992708474,1872.6321609074305,2.1365429885578084,0.0,8.333333333333332
CatBoost,37.49999999999999,33.304508592545844,151.65138058258532,0.779223560829291,0.0,0.0
AutoARIMA,33.333333333333336,25.693557606338423,0.0,16.966581296927224,0.0,16.666666666666664
Stat. Ensemble,29.79166666666667,13.462321560207968,0.0,107.0230329237857,0.0,16.666666666666664
LightGBM,29.375,28.327668712071517,8.723202911800314,0.5941772642042911,0.0,0.0
Seasonal Naive,20.3125,0.0,0.0,0.5226379387028302,0.0,0.0
AutoTheta,18.749999999999996,-8.679221746369192,0.0,4.489498287272854,0.0,0.0
AutoETS,18.229166666666664,-57.991659118752125,0.0,3.5860189728571426,0.0,12.5
Naive,10.833333333333332,-93.34435531340436,0.0,0.5319220605854591,0.0,0.0
Drift,2.5,-103.16658810164463,0.0,0.5097226914596436,0.0,0.0