# Logical Reasoning on LSAT HELM Source: [Logical Reasoning on LSAT HELM]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:35.968Z Evaluation of model performance on logical reasoning tasks using the LSAT HELM dataset, measured by Balanced classification 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 | Logical Reasoning | | Dataset (including any stated split) | LSAT HELM | | Metric | Balanced Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Balanced Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Balanced Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Base-Best | 24.38 | Not recorded | 6993f5f59ebc499c974099b1 | | Logistic Regression | 22.62 | Not recorded | 6993f5f59ebc499c974099b1 | | Dawid-Skene | 21.9 | Not recorded | 6993f5f59ebc499c974099b1 | | Voting | 21.59 | Not recorded | 6993f5f59ebc499c974099b1 | | SML | 21.59 | Not recorded | 6993f5f59ebc499c974099b1 | | WAwA | 21.44 | Not recorded | 6993f5f59ebc499c974099b1 | | U-StackingNet | 21.38 | Not recorded | 6993f5f59ebc499c974099b1 | | EBCC | 21.11 | Not recorded | 6993f5f59ebc499c974099b1 | | LAA | 20.55 | Not recorded | 6993f5f59ebc499c974099b1 | | PM | 20.1 | Not recorded | 6993f5f59ebc499c974099b1 | | LA | 19.98 | Not recorded | 6993f5f59ebc499c974099b1 | | S-StackingNet | 19.85 | Not recorded | 6993f5f59ebc499c974099b1 | | MACE | 19.81 | Not recorded | 6993f5f59ebc499c974099b1 | | GLAD | 19.76 | Not recorded | 6993f5f59ebc499c974099b1 | | ZenCrowd | 19.72 | Not recorded | 6993f5f59ebc499c974099b1 | | M-MSR | 19.28 | Not recorded | 6993f5f59ebc499c974099b1 | | Base-Worst | 19.07 | Not recorded | 6993f5f59ebc499c974099b1 | ### Base-Best Balanced Accuracy: 24.38. Result ID: 699a7b975698665ec40507f8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Logistic Regression Balanced Accuracy: 22.62. Result ID: 699a7b975698665ec4050806. [Reporting paper]() Recorded evaluation configuration: {"Mode":"Supervised"}. This record does not assert independent reproduction. ### Dawid-Skene Balanced Accuracy: 21.9. Result ID: 699a7b975698665ec40507fb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Voting Balanced Accuracy: 21.59. Result ID: 699a7b975698665ec40507f9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SML Balanced Accuracy: 21.59. Result ID: 699a7b975698665ec40507ff. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### WAwA Balanced Accuracy: 21.44. Result ID: 699a7b975698665ec40507fa. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### U-StackingNet Balanced Accuracy: 21.38. Result ID: 699a7b975698665ec4050805. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Unsupervised"}. This record does not assert independent reproduction. ### EBCC Balanced Accuracy: 21.11. Result ID: 699a7b975698665ec4050802. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LAA Balanced Accuracy: 20.55. Result ID: 699a7b975698665ec4050801. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PM Balanced Accuracy: 20.1. Result ID: 699a7b975698665ec4050803. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LA Balanced Accuracy: 19.98. Result ID: 699a7b975698665ec4050800. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### S-StackingNet Balanced Accuracy: 19.85. Result ID: 699a7b975698665ec4050807. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Supervised"}. This record does not assert independent reproduction. ### MACE Balanced Accuracy: 19.81. Result ID: 699a7b975698665ec40507fd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLAD Balanced Accuracy: 19.76. Result ID: 699a7b975698665ec40507fe. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ZenCrowd Balanced Accuracy: 19.72. Result ID: 699a7b975698665ec4050804. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### M-MSR Balanced Accuracy: 19.28. Result ID: 699a7b975698665ec40507fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base-Worst Balanced Accuracy: 19.07. Result ID: 699a7b975698665ec40507f7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.