# Reward Modeling on UltraFeedback Cleaned Source: [Reward Modeling on UltraFeedback Cleaned]() Collection index: [llms.txt]() Data updated: 2026-03-06T08:28:42.694Z Evaluation of model performance on the UltraFeedback Cleaned dataset for the Reward Modeling task, measured by the Total score. 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 | Reward Modeling | | Dataset (including any stated split) | UltraFeedback Cleaned | | Metric | Total Score | | 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 - [Total Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Total Score | Result date | Report paper | | --- | --- | --- | --- | | VRM | 92.36 | Not recorded | 69aa5f712d603e6de3e4182a | | RM | 88.98 | Not recorded | 69aa5f712d603e6de3e4182a | | SELECTIVE DPO | 82.28 | Not recorded | 69aa5f712d603e6de3e4182a | | DPO | 75.71 | Not recorded | 69aa5f712d603e6de3e4182a | | KTO | 70.67 | Not recorded | 69aa5f712d603e6de3e4182a | | IPO | 60.69 | Not recorded | 69aa5f712d603e6de3e4182a | | SIMPO | 59.16 | Not recorded | 69aa5f712d603e6de3e4182a | | WPO | 54.74 | Not recorded | 69aa5f712d603e6de3e4182a | ### VRM Total Score: 92.36. Result ID: 69aa8f416dbb7075b9544a3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RM Total Score: 88.98. Result ID: 69aa8f416dbb7075b9544a3e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SELECTIVE DPO Total Score: 82.28. Result ID: 69aa8f416dbb7075b9544a3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DPO Total Score: 75.71. Result ID: 69aa8f416dbb7075b9544a38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### KTO Total Score: 70.67. Result ID: 69aa8f416dbb7075b9544a3a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IPO Total Score: 60.69. Result ID: 69aa8f416dbb7075b9544a39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SIMPO Total Score: 59.16. Result ID: 69aa8f416dbb7075b9544a3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### WPO Total Score: 54.74. Result ID: 69aa8f416dbb7075b9544a3c. [Reporting paper]() [Method origin 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.