# DFT energy prediction on ANI-Al Source: [DFT energy prediction on ANI-Al]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:49:27.109Z Evaluation of models on predicting DFT energies using the ANI-Al dataset, typically measured by Mean Absolute Error (MAE) at both configuration and atom levels. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | DFT energy prediction | | Dataset (including any stated split) | ANI-Al | | Metric | MAE (Config, eV) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [MAE (Config, eV)](): Lower is better; unit: SCALAR. - [MAE (Atom, eV/atom)](): Lower is better; unit: SCALAR. - [Improvement](): Higher is better; unit: SCALAR. ## Recorded results | Method | MAE (Config, eV) | Result date | Report paper | | --- | --- | --- | --- | | SchNet | 0.0816 | Not recorded | 68fa42b71e209131ce90470d | | SchNet | 0.0845 | Not recorded | 68fa42b71e209131ce90470d | | SchNet | 0.1296 | Not recorded | 68fa42b71e209131ce90470d | | CGCNN | 0.1392 | Not recorded | 68fa42b71e209131ce90470d | | SchNet | 0.1693 | Not recorded | 68fa42b71e209131ce90470d | | SOAPNet | 0.1697 | Not recorded | 68fa42b71e209131ce90470d | | SOAPNet | 0.1744 | Not recorded | 68fa42b71e209131ce90470d | | SOAPNet | 0.1786 | Not recorded | 68fa42b71e209131ce90470d | | CGCNN | 0.1786 | Not recorded | 68fa42b71e209131ce90470d | | SOAPNet | 0.2153 | Not recorded | 68fa42b71e209131ce90470d | | CGCNN | 0.2206 | Not recorded | 68fa42b71e209131ce90470d | | CGCNN | 0.241 | Not recorded | 68fa42b71e209131ce90470d | | Best EIP | 46.4869 | Not recorded | 68fa42b71e209131ce90470d | ### SchNet MAE (Config, eV): 0.0816. Result ID: 698b99867a967eddb76fed81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### SchNet MAE (Config, eV): 0.0845. Result ID: 698b99867a967eddb76fed7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### SchNet MAE (Config, eV): 0.1296. Result ID: 698b99867a967eddb76fed80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### CGCNN MAE (Config, eV): 0.1392. Result ID: 698b99867a967eddb76fed85. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### SchNet MAE (Config, eV): 0.1693. Result ID: 698b99867a967eddb76fed7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### SOAPNet MAE (Config, eV): 0.1697. Result ID: 698b99867a967eddb76fed7d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### SOAPNet MAE (Config, eV): 0.1744. Result ID: 698b99867a967eddb76fed7c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### SOAPNet MAE (Config, eV): 0.1786. Result ID: 698b99867a967eddb76fed7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### CGCNN MAE (Config, eV): 0.1786. Result ID: 698b99867a967eddb76fed83. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":true,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### SOAPNet MAE (Config, eV): 0.2153. Result ID: 698b99867a967eddb76fed7a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### CGCNN MAE (Config, eV): 0.2206. Result ID: 698b99867a967eddb76fed84. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":true}. This record does not assert independent reproduction. ### CGCNN MAE (Config, eV): 0.241. Result ID: 698b99867a967eddb76fed82. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":false}. This record does not assert independent reproduction. ### Best EIP MAE (Config, eV): 46.4869. Result ID: 698b99867a967eddb76fed79. [Reporting paper]() Recorded evaluation configuration: {"Label Augmentation":false,"Multi-task Pretraining":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.