fev-bench / tables /frequency_monthly_plus /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-2,88.82352941176471,32.50619254796663,0.0,0.1675622006451613,0.0,0.0
TiRex,87.3529411764706,31.864956165412174,0.0,0.1428734488764045,0.0,0.0
Stat. Ensemble,78.52941176470587,30.6194130690149,0.0,56.487774234313726,0.0,0.0
FlowState,77.05882352941174,29.756158497560868,0.0,0.8030137029411765,0.11764705882352941,0.0
TabPFN-TS,72.05882352941175,29.111909362943443,0.0,53.464398235686275,0.0,0.0
TimesFM-2.5,67.94117647058823,27.453887143184406,0.0,0.300447106741573,0.11764705882352941,0.0
AutoETS,66.47058823529412,23.93881415260619,0.0,0.9996816480645161,0.0,0.0
Toto-1.0,60.29411764705881,25.340510079762048,0.0,4.575649140757576,0.11764705882352941,0.0
Chronos-Bolt,58.38235294117647,25.546718735921615,0.0,0.11144018651685393,0.0,0.0
AutoARIMA,56.470588235294116,25.353548156637395,0.0,4.093532921161616,0.0,0.0
Moirai-2.0,50.44117647058823,22.311614601785536,0.0,0.2131613306839772,0.17647058823529413,0.0
AutoTheta,49.41176470588234,22.773093515453148,0.0,0.7425851477450981,0.0,0.0
DeepAR,42.35294117647059,18.95227595931224,375.9662100911765,0.15036647323529412,0.0,0.0
Drift,34.411764705882355,7.532134770506794,0.0,0.414788997254902,0.0,0.0
PatchTST,28.38235294117647,11.558604544866135,269.84668655656867,0.15002605903225805,0.0,0.0
LightGBM,26.764705882352942,13.644306827349173,0.10358782967741936,0.03398107580645161,0.0,0.0
TFT,24.55882352941176,6.970181833006062,331.95714435490197,0.16816778392156864,0.0,0.0
CatBoost,22.94117647058823,13.157433589700718,2.6764738721212122,0.03868938677419355,0.0,0.0
Sundial-Base,22.35294117647059,9.655963998764527,0.0,7.9919304493548395,0.0,0.0
Seasonal Naive,17.64705882352941,0.0,0.0,0.38861874,0.0,0.0
Naive,17.352941176470587,-2.4793582422915295,0.0,0.40925864460784306,0.0,0.0