# EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets

DevFeed: [EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets](<https://devfeed.tech/articles/energybench-a-live-gate-aligned-benchmark-of-day-ahead-forecasts-for-european-power-markets-120667.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07784>)

Author: Evgenii Genov, Ander Martinez Alonso, Christoph Bergmeir

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [benchmark overfitting machine learning](<https://devfeed.tech/topics/benchmark-overfitting-machine-learning.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [markets](<https://devfeed.tech/tags/markets.md>), [power](<https://devfeed.tech/tags/power.md>), [time-series-foundation-models](<https://devfeed.tech/tags/time-series-foundation-models.md>)

## AI overview

EnergyBench runs forecasts live at 11:30 CET/CEST, freezes and publishes the shared information set--including three weather models--and evaluates next-day 15-minute prices, wind, solar and load across six European bidding zones. This gate-aligned setup avoids relying on fixed test sets and lets foundation models be compared with and without the same weather covariates. In its first 32 live days, covariates cut error by 37-51% for each of ten matched foundation models (64-73% for wind and 48-61% for solar). Used zero-shot, the models matched or beat LightGBM trained on those covariates; model size mattered less, and median ensembles ranked highest. Grid operators' pre-gate forecasts still had lower wind and solar error: the best single foundation models had 16-22% more error. The load gap was 4-6%, within the reported intervals.

## Source excerpt

arXiv:2611.07784v1 Announce Type: new Abstract: Energy forecasting models are usually compared on backtests and fixed public datasets. Backtests can use data that did not yet exist when the forecast would have been made, and a fixed test set, reused across studies and possibly contained in the pretraining data of foundation models, invites overfitting to the benchmark. EnergyBench evaluates every entry live instead. Each day at 11:30 CET/CEST, thirty minutes before the day-ahead (SDAC) gate closes, every model forecasts the next day's price, wind and solar generation and load on the 15-minute grid for six bidding zones (BE, NL, FR, DE-LU, DK1, DK2). Unlike existing live benchmarks, EnergyBench runs the models itself, on one information set that it freezes at the cut-off and publishes, including three numerical weather prediction models, so that foundation models can be compared with and without the same weather covariates under the actual market deadline. Errors are pooled per series against a seasonal-naive baseline, and models are ranked by a Bradley-Terry rating on the Elo scale with a day-bootstrap interval. The field spans baselines, linear and gradient-boosted models on the frozen weather, eighteen time-series foundation models from eleven families, ensembles, and the grid operators' own forecasts. Over the first thirty-two live days, the covariates reduced the error of each of the ten foundation models run with and without them by 37-51% on matched races (64-73% on wind, 48-61% on solar). Used zero-shot, these models match or outperform a LightGBM model trained on the same covariates. Model size, from 3M to 331M parameters, has a much smaller effect, and median ensembles of the covariate models rank highest. The grid operators' pre-gate forecasts remain ahead on wind and solar, where the best single foundation models have 16-22% more error; on load the gap is 4-6%, within the intervals.