# Interatomic Potential Modeling on Ta-V-Cr-W 1.0 (Original splits Overall) Source: [Interatomic Potential Modeling on Ta-V-Cr-W 1.0 (Original splits Overall)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:18.531Z Evaluation of interatomic potential models on the Ta-V-Cr-W 1.0 dataset (using original splits), focusing on energy and force accuracy measured by RMSE, alongside computational performance metrics like inference time and memory usage. 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 | Interatomic Potential Modeling | | Dataset (including any stated split) | Ta-V-Cr-W 1.0 (Original splits Overall) | | Metric | E-RMSE (meV/atom) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 10 of 10 | | 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 - [E-RMSE (meV/atom)](): Lower is better; unit: SCALAR. - [F-RMSE (eV/Å)](): Lower is better; unit: SCALAR. - [Inference time (µs/atom)](): Lower is better; unit: TIME. - [Memory consumption (GB)](): Lower is better; unit: SIZE. ## Recorded results | Method | E-RMSE (meV/atom) | Result date | Report paper | | --- | --- | --- | --- | | ICTPsym | 1.38 | Not recorded | 68fa48621e209131ce92f362 | | ICTPsym | 1.56 | Not recorded | 68fa48621e209131ce92f362 | | MACE | 1.67 | Not recorded | 68fa48621e209131ce92f362 | | ICTPsym | 1.67 | Not recorded | 68fa48621e209131ce92f362 | | MACE | 2.19 | Not recorded | 68fa48621e209131ce92f362 | | GM-NN | 2.32 | Not recorded | 68fa48621e209131ce92f362 | | MACE | 2.42 | Not recorded | 68fa48621e209131ce92f362 | | MTP | 2.43 | Not recorded | 68fa48621e209131ce92f362 | | ICTPsym | 3.17 | Not recorded | 68fa48621e209131ce92f362 | | EAM | 37.14 | Not recorded | 68fa48621e209131ce92f362 | ### ICTPsym E-RMSE (meV/atom): 1.38. Result ID: 698b9e407a967eddb770131a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"L":2,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### ICTPsym E-RMSE (meV/atom): 1.56. Result ID: 698b9e407a967eddb770131b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"L":1,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### MACE E-RMSE (meV/atom): 1.67. Result ID: 698b9e407a967eddb770131d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"L":2,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### ICTPsym E-RMSE (meV/atom): 1.67. Result ID: 698b9e407a967eddb7701320. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"V":2,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### MACE E-RMSE (meV/atom): 2.19. Result ID: 698b9e407a967eddb770131e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"L":1,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### GM-NN E-RMSE (meV/atom): 2.32. Result ID: 698b9e407a967eddb7701322. [Reporting paper]() Recorded evaluation configuration: {"Batch size":50,"Hardware":"NVIDIA GeForce RTX 3090 Ti"}. This record does not assert independent reproduction. ### MACE E-RMSE (meV/atom): 2.42. Result ID: 698b9e407a967eddb770131f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"L":0,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### MTP E-RMSE (meV/atom): 2.43. Result ID: 698b9e407a967eddb7701321. [Reporting paper]() Recorded evaluation configuration: {"Batch size":50,"Hardware":"Intel Xeon E6252 Gold"}. This record does not assert independent reproduction. ### ICTPsym E-RMSE (meV/atom): 3.17. Result ID: 698b9e407a967eddb770131c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"L":0,"Batch size":50,"Hardware":"NVIDIA A100 GPU"}. This record does not assert independent reproduction. ### EAM E-RMSE (meV/atom): 37.14. Result ID: 698b9e407a967eddb7701323. [Reporting paper]() Recorded evaluation configuration: {"Batch size":50,"Hardware":"Intel Xeon E6252 Gold"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.