fev-bench / tables /leaderboard_WQL.csv
shchuro's picture
Add tables
18a3564
raw
history blame
1.15 kB
model_name,win_rate,skill_score,median_training_time_s,median_inference_time_s,training_corpus_overlap,num_failures
TiRex,84.65384615384616,46.66550397812589,0.0,1.4030189444999999,0.01,0.0
TimesFM-2.5,82.53846153846153,46.80188214969573,0.0,117.557863139,0.08,0.0
Toto-1.0,73.92307692307693,45.00088243993733,0.0,90.676829282,0.08,0.0
TabPFN-TS,71.88461538461539,45.822378843833036,0.0,305.466367349,0.0,2.0
Moirai-2.0,70.15384615384615,43.864523387242194,0.0,2.5351729785000003,0.28,0.0
Chronos-Bolt,69.0,43.187343947848866,0.0,0.9960156920000001,0.0,0.0
Sundial-Base,50.42307692307693,37.43731640370259,0.0,35.620029862500004,0.01,0.0
Stat. Ensemble,47.1923076923077,21.795752415252334,0.0,690.615290623,0.0,11.0
AutoARIMA,42.884615384615394,23.401617100945593,0.0,186.7699845295,0.0,10.0
AutoETS,33.42307692307693,-27.026777935471568,0.0,17.004582018,0.0,3.0
AutoTheta,28.61538461538461,7.846425960422055,0.0,9.267665384499999,0.0,0.0
Seasonal Naive,20.807692307692307,0.0,0.0,2.3247850175,0.0,0.0
Naive,14.653846153846157,-39.121433468308894,0.0,2.2371214229999996,0.0,0.0
Drift,9.846153846153847,-40.05851008470427,0.0,2.1929671395000003,0.0,0.0