Codesota · Benchmark · ETTh1Home/Leaderboards/Structured Data & Forecasting/Time-Series Forecasting/ETTh1
Unknown

ETTh1.

ETTh1 is one of four ETT benchmark datasets for long-term time series forecasting. It records electricity transformer oil temperature and load at hourly granularity from a power station in China (July 2016 – July 2018). Results reported as averages across prediction horizons {96, 192, 336, 720}.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Only 3 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Mse

Mse is the reported evaluation metric for ETTh1. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Mseverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Chronos-Large
Averaged across horizons {96,192,336,720}. Source: Sundial paper Table 1.
verified0.592025Paper ↗Looks wrong?
02TimesFM
Averaged across horizons {96,192,336,720}. Source: Sundial paper Table 1.
verified0.472025Paper ↗Looks wrong?
03TimeLLM
Per-horizon MSE (0.377,0.414,0.447,0.554) avg=0.448; MAE (0.405,0.431,0.457,0.529) avg=0.456. Source: arxiv:2504.08808 Table 11.
verified0.452024Paper ↗Code ↗Source ↗Looks wrong?

Mae

Mae is the reported evaluation metric for ETTh1. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Maeverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Chronos-Large
Averaged across horizons {96,192,336,720}. Source: Sundial paper Table 1.
verified0.472025Paper ↗Looks wrong?
02TimeLLM
Per-horizon MSE (0.377,0.414,0.447,0.554) avg=0.448; MAE (0.405,0.431,0.457,0.529) avg=0.456. Source: arxiv:2504.08808 Table 11.
verified0.462024Paper ↗Code ↗Source ↗Looks wrong?
03TimesFM
Averaged across horizons {96,192,336,720}. Source: Sundial paper Table 1.
verified0.442025Paper ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Time-Series Forecasting