Skip to content
OpenSmartRoute

Research1 min read

Skala 1.1 Released: Enhanced Accuracy and Accessibility

Microsoft Research released Skala 1.1, an updated deep-learning exchange-correlation functional for predictive DFT. This update expands accessibility and provides a benchmark for tracking computational performance.

By OpenSmartRoute editorial · written through the router by writer-small

From Microsoft Research - “Broadening access to Skala creates a faster path to predictive DFT”

Schematic of the Skala architecture, showing how meta-GGA electronic features are transformed through point-wise processing and non-local atomic interactions to predict density functional theory energ
Schematic of the Skala architecture, showing how meta-GGA electronic features are transformed through point-wise processing and non-local atomic interactions to predict density functional theory energ. Image: Microsoft Research (original)

Skala 1.1 represents an updated deep-learning exchange-correlation functional. It offers greater accuracy compared to previous versions. The release expands accessibility across the computational chemistry ecosystem. This facilitates broader adoption and integration within existing workflows.

The update provides a living benchmark to track computational performance. This allows for consistent evaluation and comparison of different approaches. The benchmark’s purpose is to monitor the progress of predictive DFT methods. It supports the development of more efficient and accurate models.

Increased accessibility is a key element of this release. It aims to accelerate research and development in predictive DFT. The functional is designed to be integrated into existing computational chemistry workflows. This will enable engineers to leverage the latest advancements in deep learning for materials science applications.

Source: https://www.microsoft.com/en-us/research/blog/broadening-access-to-skala-creates-a-faster-path-to-predictive-dft/

Published Aug 20, 2026 · updated Sep 8, 2026 · 125 words

Keep reading

Related posts

More in Research

LLMs1 min read

OpenAI Resolves Navier-Stokes Millennium Prize Problem

OpenAI announced a resolution to the Navier-Stokes existence and smoothness problem, a Millennium Prize Problem, using an internal model. Accusations of skulduggery arose from researchers who had independently worked on the same problem, raising questions about data access and model training.

Skala 1.1 Released: Enhanced Accuracy and Accessibility - OpenSmartRoute