fev-bench / tables /frequency_daily /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-2,90.0,40.241553705242325,0.0,0.35793460493470153,0.0,0.0
TiRex,86.75,35.70932536691862,0.0,0.1291116508215071,0.0,0.0
TimesFM-2.5,85.50000000000001,36.21512359135406,0.0,0.575423012749835,0.1,0.0
Moirai-2.0,79.25,35.235748193480255,0.0,0.24187414339990285,0.4,0.0
Chronos-Bolt,77.75000000000001,34.57369581909669,0.0,0.13213293969508144,0.0,0.0
FlowState,73.25000000000001,33.231151028003566,0.0,0.8854096169209039,0.1,0.0
Toto-1.0,71.0,33.533977961386974,0.0,10.283148248083332,0.1,0.0
TabPFN-TS,67.875,34.19450526988148,0.0,79.45039829948598,0.0,5.0
Sundial-Base,51.74999999999999,26.539906909008327,0.0,8.099000643582091,0.0,0.0
TFT,48.12500000000001,22.27606386903942,323.36690221656073,0.2700071295171898,0.0,0.0
Stat. Ensemble,46.75000000000001,24.79006525446703,0.0,145.59674209388467,0.0,0.0
AutoARIMA,41.75,21.22121308421785,0.0,73.60630374002452,0.0,0.0
AutoETS,38.25,20.120766929488475,0.0,3.3519659038334995,0.0,0.0
PatchTST,34.25,14.9301643137155,287.64413890660023,0.2739963583326908,0.0,0.0
DeepAR,32.12499999999999,14.294397638336442,491.09394703656005,0.4963672847508972,0.0,0.0
AutoTheta,31.25,15.776905337592694,0.0,3.0638472506820937,0.0,0.0
CatBoost,31.0,13.347203632390958,17.24107904783333,0.14455932012545694,0.0,0.0
LightGBM,30.999999999999993,13.191993375720667,1.2347621929848485,0.1353946523502825,0.0,0.0
Seasonal Naive,19.124999999999996,0.0,0.0,0.3410607536415753,0.0,0.0
Naive,8.75,-43.691472811269946,0.0,0.31280659340063144,0.0,0.0
Drift,4.500000000000001,-44.75542175816074,0.0,0.3111704808059156,0.0,0.0