Codesota · Benchmark · WeatherHome/Leaderboards/Structured Data & Forecasting/Time-Series Forecasting/Weather
Unknown

Weather.

The Weather dataset contains 21 meteorological indicators (temperature, humidity, wind speed, etc.) recorded every 10 minutes at a weather station in Germany for 2020. Widely used for long-term multivariate forecasting benchmarks. Results reported as averages across prediction horizons {96, 192, 336, 720}.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Mae

Mae is the reported evaluation metric for Weather. 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
01DLinear
Averaged across horizons {96,192,336,720}. DLinear result from iTransformer comparison table.
verified0.322024Paper ↗Code ↗Looks wrong?
02Chronos-Large
Averaged across horizons {96,192,336,720}.
verified0.312025Paper ↗Looks wrong?
03TimesNet
Averaged across horizons {96,192,336,720}. TimesNet result from iTransformer comparison table.
verified0.292024Paper ↗Code ↗Looks wrong?
04PatchTST
Averaged across horizons {96,192,336,720}. PatchTST result from iTransformer comparison table.
verified0.282024Paper ↗Code ↗Looks wrong?
05iTransformer
Averaged across horizons {96,192,336,720}. From Table 1 iTransformer paper.
verified0.282024Paper ↗Code ↗Looks wrong?
06TimeLLM
Per-horizon MSE (0.156,0.200,0.249,0.317) avg=0.231; MAE (0.208,0.249,0.285,0.332) avg=0.269.
verified0.272024Paper ↗Code ↗Source ↗Looks wrong?

Mse

Mse is the reported evaluation metric for Weather. 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}.
verified0.282025Paper ↗Looks wrong?
02DLinear
Averaged across horizons {96,192,336,720}. DLinear result from iTransformer comparison table.
verified0.272024Paper ↗Code ↗Looks wrong?
03TimesNet
Averaged across horizons {96,192,336,720}. TimesNet result from iTransformer comparison table.
verified0.262024Paper ↗Code ↗Looks wrong?
04PatchTST
Averaged across horizons {96,192,336,720}. PatchTST result from iTransformer comparison table.
verified0.262024Paper ↗Code ↗Looks wrong?
05iTransformer
Averaged across horizons {96,192,336,720}. From Table 1 iTransformer paper.
verified0.262024Paper ↗Code ↗Looks wrong?
06TimeLLM
Per-horizon MSE (0.156,0.200,0.249,0.317) avg=0.231; MAE (0.208,0.249,0.285,0.332) avg=0.269.
verified0.232024Paper ↗Code ↗Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Time-Series Forecasting
Weather Leaderboard | CodeSOTA | CodeSOTA