# Multi-step Mathematical Reasoning on DART 5 Source: [Multi-step Mathematical Reasoning on DART 5]() Collection index: [llms.txt]() Data updated: 2026-03-17T07:21:32.235Z Evaluation of model performance on multi-step mathematical reasoning using the DART 5 dataset, measured by accuracy and delta. 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 | multi-step mathematical reasoning | | Dataset (including any stated split) | DART 5 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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. - [Delta](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Berr. Latent | 54 | Not recorded | 69b8e0040636e5bf4afbe967 | | Berr. Text | 27 | Not recorded | 69b8e0040636e5bf4afbe967 | | LLaDA + Sonnet Plan | 17.2 | Not recorded | 69b8e0040636e5bf4afbe967 | | Berr. BL | 15 | Not recorded | 69b8e0040636e5bf4afbe967 | | LLaDA | 11 | Not recorded | 69b8e0040636e5bf4afbe967 | ### Berr. Latent Accuracy: 54. Result ID: 69b900f547f34ce924a113bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Collaboration space":"Latent-space","Description":"Best latent-space DDLM→ARM result","Projector training":"trained Linear-GELU-Linear projector on 35K domain-specific samples"}. This record does not assert independent reproduction. ### Berr. Text Accuracy: 27. Result ID: 69b900f547f34ce924a113ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Collaboration space":"Text-space","Description":"Best text-space collaboration result"}. This record does not assert independent reproduction. ### LLaDA + Sonnet Plan Accuracy: 17.2. Result ID: 69b900f547f34ce924a113b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Plan conditioning":"Sonnet Plan"}. This record does not assert independent reproduction. ### Berr. BL Accuracy: 15. Result ID: 69b900f547f34ce924a113b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Description":"LLaDA-only baseline by Berrayana et al."}. This record does not assert independent reproduction. ### LLaDA Accuracy: 11. Result ID: 69b900f547f34ce924a113b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Description":"LLaDA-only baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.