2026 AI Weather Model Benchmarks: EPT-2 Leads

1 / 5

WeatherBench 2 measures global structural skill against ERA5, while StationBench measures point-level accuracy against more than 10,000 real surface stations that match how assets earn or lose money.

2 / 5

EPT-2 leads the 2026 benchmarks, beating ECMWF HRES across all lead times from 0–240 hours on the four energy-critical surface variables and extending the advantage previously shown by EPT-1.5 on European wind and temperature.

3 / 5

EPT-2e surpasses the 50-member ECMWF ENS mean on both RMSE and CRPS at virtually every lead time, becoming the first productised AI ensemble to outperform the long-standing probabilistic NWP gold standard.

4 / 5

AI models such as Microsoft Aurora lack SSRD output entirely, which removes them from solar-generation benchmarks, while EPT-2 produces all four energy-critical variables natively at far lower inference cost.

5 / 5

Energy traders can validate these results in seconds on Jua’s live benchmarking surface and book a demo to see EPT-2 head-to-head against their current provider.