# Reward Modeling on PPE-Preference 1k Source: [Reward Modeling on PPE-Preference 1k]() Collection index: [llms.txt]() Data updated: 2026-04-10T07:20:53.333Z Evaluation of model performance on the 1,000-sample subset of the PPE-Preference dataset for the Reward Modeling task, utilizing the Positional Consistency metric. 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) | PPE-Preference 1k | | Metric | Positional Consistency | | 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 - [Positional Consistency](): Higher is better; unit: PERCENT. ## Recorded results | Method | Positional Consistency | Result date | Report paper | | --- | --- | --- | --- | | ReflectRM | 51.7 | Not recorded | 69d883e07d0172140ec77804 | | Unified Training | 48.1 | Not recorded | 69d883e07d0172140ec77804 | | RFT | 46.6 | Not recorded | 69d883e07d0172140ec77804 | | RFT | 44.6 | Not recorded | 69d883e07d0172140ec77804 | | ReflectRM | 44.3 | Not recorded | 69d883e07d0172140ec77804 | | Unified Training | 44.2 | Not recorded | 69d883e07d0172140ec77804 | | Qwen3-8B | 42.1 | Not recorded | 69d883e07d0172140ec77804 | | Qwen3-4B | 34.9 | Not recorded | 69d883e07d0172140ec77804 | ### ReflectRM Positional Consistency: 51.7. Result ID: 69d8a4ba47f34ce924c11a9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Training Method":"Unified Training","Inference Strategy":"Two-Stage Inference"}. This record does not assert independent reproduction. ### Unified Training Positional Consistency: 48.1. Result ID: 69d8a4ba47f34ce924c11a9a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Training Method":"Unified Training"}. This record does not assert independent reproduction. ### RFT Positional Consistency: 46.6. Result ID: 69d8a4ba47f34ce924c11a99. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Training Method":"RFT"}. This record does not assert independent reproduction. ### RFT Positional Consistency: 44.6. Result ID: 69d8a4ba47f34ce924c11a9d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Training Method":"RFT"}. This record does not assert independent reproduction. ### ReflectRM Positional Consistency: 44.3. Result ID: 69d8a4ba47f34ce924c11a9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Training Method":"Unified Training","Inference Strategy":"Two-Stage Inference"}. This record does not assert independent reproduction. ### Unified Training Positional Consistency: 44.2. Result ID: 69d8a4ba47f34ce924c11a9e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Training Method":"Unified Training"}. This record does not assert independent reproduction. ### Qwen3-8B Positional Consistency: 42.1. Result ID: 69d8a4ba47f34ce924c11a9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Qwen3-4B Positional Consistency: 34.9. Result ID: 69d8a4ba47f34ce924c11a98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.