# Premise Selection on HolStep (test) Source: [Premise Selection on HolStep (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:22.421Z Evaluation of model performance on the Premise Selection task using the test split of the HolStep dataset, typically measured by accuracy. 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 | Premise Selection | | Dataset (including any stated split) | HolStep (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FormulaNet | 90.3 | Not recorded | 68fa63ba1e209131cea00732 | | FormulaNet-basic | 89.1 | Not recorded | 68fa63ba1e209131cea00732 | | CNN-LSTM | 83 | Not recorded | 68fa63ba1e209131cea00732 | | CNN | 82 | Not recorded | 68fa63ba1e209131cea00732 | | FormulaNet | 0.9 | Not recorded | 68fa63ba1e209131cea00732 | | FormulaNet-basic | 0.89 | Not recorded | 68fa63ba1e209131cea00732 | | CNN | 0.83 | Not recorded | 68fa63ba1e209131cea00732 | | CNN-LSTM | 0.83 | Not recorded | 68fa63ba1e209131cea00732 | ### FormulaNet Accuracy: 90.3. Result ID: 698c786d37894ef7d9ce9c1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"conditional"}. This record does not assert independent reproduction. ### FormulaNet-basic Accuracy: 89.1. Result ID: 698c786d37894ef7d9ce9c1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"conditional"}. This record does not assert independent reproduction. ### CNN-LSTM Accuracy: 83. Result ID: 698c786d37894ef7d9ce9c1c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"conditional"}. This record does not assert independent reproduction. ### CNN Accuracy: 82. Result ID: 698c786d37894ef7d9ce9c1b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"conditional"}. This record does not assert independent reproduction. ### FormulaNet Accuracy: 0.9. Result ID: 698c00f0f729bc7f68e78fdb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"unconditional"}. This record does not assert independent reproduction. ### FormulaNet-basic Accuracy: 0.89. Result ID: 698c00f0f729bc7f68e78fda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"unconditional"}. This record does not assert independent reproduction. ### CNN Accuracy: 0.83. Result ID: 698c00f0f729bc7f68e78fd8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"unconditional"}. This record does not assert independent reproduction. ### CNN-LSTM Accuracy: 0.83. Result ID: 698c00f0f729bc7f68e78fd9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"unconditional"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.