# Handwritten digit classification on MNIST (test) Source: [Handwritten digit classification on MNIST (test)]() Collection index: [llms.txt]() Data updated: 2026-05-04T08:51:43.376Z Evaluation of Handwritten Digit Classification performance on the test split of the MNIST dataset, reporting structural or graph-based metrics. 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 | Handwritten digit classification | | Dataset (including any stated split) | MNIST (test) | | Metric | Accuracy (Regular) | | Unit | PERCENT | | Direction | Higher 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 - [Accuracy (Regular)](): Higher is better; unit: PERCENT. - [Accuracy (Complete)](): Higher is better; unit: PERCENT. - [Accuracy (Ring)](): Higher is better; unit: PERCENT. - [Accuracy (Erdős–Rényi)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Regular) | Result date | Report paper | | --- | --- | --- | --- | | CIL | 97.79 | Not recorded | 6965d1a46343fa78c8323807 | | Standard SGD | 97.42 | Not recorded | 6965d1a46343fa78c8323807 | | DeCaFork | 97.31 | Not recorded | 6965d1a46343fa78c8323807 | | CIL | 97.16 | Not recorded | 6965d1a46343fa78c8323807 | | Structured Recurrent SNN | 97 | Not recorded | 69f82816c0f56ed843088ac3 | | STDP | 95 | Not recorded | 69f82816c0f56ed843088ac3 | | e-prop | 92 | Not recorded | 69f82816c0f56ed843088ac3 | | Reward-modulated STDP | 88 | Not recorded | 69f82816c0f56ed843088ac3 | | WTA-based SNN | 88 | Not recorded | 69f82816c0f56ed843088ac3 | | Reservoir SNN + readout | 85 | Not recorded | 69f82816c0f56ed843088ac3 | ### CIL Accuracy (Regular): 97.79. Result ID: 6999a8025698665ec41ecae8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partitioning":"i.i.d.","A (hyperparameter)":"small (A=10)"}. This record does not assert independent reproduction. ### Standard SGD Accuracy (Regular): 97.42. Result ID: 6999a8025698665ec41ecae7. [Reporting paper]() Recorded evaluation configuration: {"Data Partitioning":"i.i.d."}. This record does not assert independent reproduction. ### DeCaFork Accuracy (Regular): 97.31. Result ID: 6999a8025698665ec41ecaea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partitioning":"i.i.d."}. This record does not assert independent reproduction. ### CIL Accuracy (Regular): 97.16. Result ID: 6999a8025698665ec41ecae9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Partitioning":"i.i.d.","A (hyperparameter)":"large (A=350)"}. This record does not assert independent reproduction. ### Structured Recurrent SNN Accuracy (Regular): 97. Result ID: 69f85e0447f34ce924dc31b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning rule":"WTA + modulatory plasticity","Depth / Recurrence":"Deep recurrent"}. This record does not assert independent reproduction. ### STDP Accuracy (Regular): 95. Result ID: 69f85e0447f34ce924dc31ab. [Reporting paper]() Recorded evaluation configuration: {"Learning rule":"Unsupervised STDP + readout","Depth / Recurrence":"Shallow, feedforward"}. This record does not assert independent reproduction. ### e-prop Accuracy (Regular): 92. Result ID: 69f85e0447f34ce924dc31af. [Reporting paper]() Recorded evaluation configuration: {"Learning rule":"Approx. gradient descent","Depth / Recurrence":"Deep recurrent"}. This record does not assert independent reproduction. ### Reward-modulated STDP Accuracy (Regular): 88. Result ID: 69f85e0447f34ce924dc31ad. [Reporting paper]() Recorded evaluation configuration: {"Learning rule":"Three-factor plasticity","Depth / Recurrence":"Shallow / recurrent"}. This record does not assert independent reproduction. ### WTA-based SNN Accuracy (Regular): 88. Result ID: 69f85e0447f34ce924dc31ae. [Reporting paper]() Recorded evaluation configuration: {"Learning rule":"Margin / competition","Depth / Recurrence":"Shallow"}. This record does not assert independent reproduction. ### Reservoir SNN + readout Accuracy (Regular): 85. Result ID: 69f85e0447f34ce924dc31ac. [Reporting paper]() Recorded evaluation configuration: {"Learning rule":"Fixed recurrence","Depth / Recurrence":"Recurrent, untrained"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.