fev-bench / tables /full /leaderboard_SQL.csv
shchuro's picture
Separate tables by subset
d4397a6
model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
Chronos-2,91.42857142857143,47.28056105322771,0.0,0.8031324525807175,0.0,0.0
TiRex,82.67857142857142,42.57610775202675,0.0,0.22657166035714288,0.01,0.0
TimesFM-2.5,77.57142857142858,42.20062128325953,0.0,1.8920524236607146,0.1,0.0
Toto-1.0,70.21428571428571,40.7460359139889,0.0,22.06562094568182,0.08,0.0
Chronos-Bolt,64.42857142857143,38.892961600022936,0.0,0.24851168673039045,0.0,0.0
Moirai-2.0,64.42857142857143,39.332013785815214,0.0,0.34801128166666667,0.28,0.0
TabPFN-TS,62.96428571428573,39.58671179038912,0.0,88.93563502960615,0.0,2.0
Sundial-Base,45.964285714285715,33.42287717226134,0.0,8.007535389309524,0.01,0.0
Stat. Ensemble,45.53571428571429,20.161731427800046,0.0,148.58311610827104,0.0,11.0
AutoARIMA,40.67857142857143,20.561948549632326,0.0,19.52332778642857,0.0,10.0
AutoETS,33.67857142857143,-26.818526760288375,0.0,3.4683364387499998,0.0,3.0
AutoTheta,27.142857142857142,5.457380397818312,0.0,3.250292683443853,0.0,0.0
Seasonal Naive,20.178571428571423,0.0,0.0,0.455576268872549,0.0,0.0
Naive,13.821428571428573,-45.398988807164976,0.0,0.45289251607142855,0.0,0.0
Drift,9.285714285714286,-45.77585379444895,0.0,0.451296885,0.0,0.0