# Latent Preference Modeling on MPT Context-Free Average Source: [Latent Preference Modeling on MPT Context-Free Average]() Collection index: [llms.txt]() Data updated: 2026-04-21T12:06:28.921Z Evaluation of model performance on the MPT Context-Free Average dataset for the Latent Preference Modeling task, measured by F1 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 | Latent Preference Modeling | | Dataset (including any stated split) | MPT Context-Free Average | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | PREFINE | 58.5 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 56.77 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 55.95 | Not recorded | 69e7050b7d0172140ec7f237 | | Gemini-3-Flash | 52.53 | Not recorded | 69e7050b7d0172140ec7f237 | | GPT-5-mini | 51.99 | Not recorded | 69e7050b7d0172140ec7f237 | | GPT-5 | 49.83 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 48.62 | Not recorded | 69e7050b7d0172140ec7f237 | | LangMem | 48.5 | Not recorded | 69e7050b7d0172140ec7f237 | | Mem0 | 46.18 | Not recorded | 69e7050b7d0172140ec7f237 | | GPT-4o-mini | 45.26 | Not recorded | 69e7050b7d0172140ec7f237 | | RAG (Top-5) | 44.88 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 44.01 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 35.03 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 33.56 | Not recorded | 69e7050b7d0172140ec7f237 | | Gemma-3-12B | 32.66 | Not recorded | 69e7050b7d0172140ec7f237 | | R1-Distill-Llama-8B | 30.96 | Not recorded | 69e7050b7d0172140ec7f237 | | PREFINE | 30.65 | Not recorded | 69e7050b7d0172140ec7f237 | | CodeGemma-7B | 19.42 | Not recorded | 69e7050b7d0172140ec7f237 | | R1-Distill-Qwen-7B | 18.59 | Not recorded | 69e7050b7d0172140ec7f237 | ### PREFINE F1 Score: 58.5. Result ID: 69e7683947f34ce924cee4da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Gemini-3-Flash"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 56.77. Result ID: 69e7683947f34ce924cee4d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"GPT-5-mini"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 55.95. Result ID: 69e7683947f34ce924cee4d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"GPT-5"}. This record does not assert independent reproduction. ### Gemini-3-Flash F1 Score: 52.53. Result ID: 69e7683947f34ce924cee4cf. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### GPT-5-mini F1 Score: 51.99. Result ID: 69e7683947f34ce924cee4cd. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### GPT-5 F1 Score: 49.83. Result ID: 69e7683947f34ce924cee4ce. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 48.62. Result ID: 69e7683947f34ce924cee4d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"GPT-4o-mini"}. This record does not assert independent reproduction. ### LangMem F1 Score: 48.5. Result ID: 69e7683947f34ce924cee4d2. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Memory-Augmented","Backbone":"Gemini-3-Flash"}. This record does not assert independent reproduction. ### Mem0 F1 Score: 46.18. Result ID: 69e7683947f34ce924cee4d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Methodology":"Memory-Augmented","Backbone":"Gemini-3-Flash"}. This record does not assert independent reproduction. ### GPT-4o-mini F1 Score: 45.26. Result ID: 69e7683947f34ce924cee4cc. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### RAG (Top-5) F1 Score: 44.88. Result ID: 69e7683947f34ce924cee4d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Methodology":"Memory-Augmented","Backbone":"Gemini-3-Flash"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 44.01. Result ID: 69e7683947f34ce924cee4d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Gemma-3-12B"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 35.03. Result ID: 69e7683947f34ce924cee4d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 33.56. Result ID: 69e7683947f34ce924cee4d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"CodeGemma-7B"}. This record does not assert independent reproduction. ### Gemma-3-12B F1 Score: 32.66. Result ID: 69e7683947f34ce924cee4c9. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### R1-Distill-Llama-8B F1 Score: 30.96. Result ID: 69e7683947f34ce924cee4ca. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### PREFINE F1 Score: 30.65. Result ID: 69e7683947f34ce924cee4d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### CodeGemma-7B F1 Score: 19.42. Result ID: 69e7683947f34ce924cee4c8. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. ### R1-Distill-Qwen-7B F1 Score: 18.59. Result ID: 69e7683947f34ce924cee4cb. [Reporting paper]() Recorded evaluation configuration: {"Methodology":"Base Prompting"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.