# Personalized Recommendation on RecBench+ Book Source: [Personalized Recommendation on RecBench+ Book]() Collection index: [llms.txt]() Data updated: 2026-04-10T08:14:48.835Z Evaluation of personalized recommendation performance using the RecBench+ Book dataset, measured across difficulty levels (Simple, Medium, Hard) and specific recommendation types (Interest-based, Demographics-based). 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 | Personalized Recommendation | | Dataset (including any stated split) | RecBench+ Book | | Metric | Performance (Simple) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Performance (Simple)](): Higher is better; unit: PERCENT. - [Performance (Medium)](): Higher is better; unit: PERCENT. - [Performance (Hard)](): Higher is better; unit: PERCENT. - [Performance (Interest-based)](): Higher is better; unit: PERCENT. - [Performance (Demographics-based)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Performance (Simple) | Result date | Report paper | | --- | --- | --- | --- | | ReRec | 67.1 | Not recorded | 69d883f87d0172140ec7795d | | GRPO | 66.4 | Not recorded | 69d883f87d0172140ec7795d | | REINFORCE++ | 66.1 | Not recorded | 69d883f87d0172140ec7795d | | RLOO | 66 | Not recorded | 69d883f87d0172140ec7795d | | RLOO | 56.7 | Not recorded | 69d883f87d0172140ec7795d | | TallRec | 56.3 | Not recorded | 69d883f87d0172140ec7795d | | GRPO | 56.3 | Not recorded | 69d883f87d0172140ec7795d | | Deepseek-R1 | 56.2 | Not recorded | 69d883f87d0172140ec7795d | | CRAG | 56 | Not recorded | 69d883f87d0172140ec7795d | | InteRecAgent | 55.7 | Not recorded | 69d883f87d0172140ec7795d | | ReRec | 55.5 | Not recorded | 69d883f87d0172140ec7795d | | GPT-4o | 55.4 | Not recorded | 69d883f87d0172140ec7795d | | REINFORCE++ | 55.3 | Not recorded | 69d883f87d0172140ec7795d | | Qwen-2.5-3B-Instruct | 37.1 | Not recorded | 69d883f87d0172140ec7795d | | Llama-3.2-3B-Instruct | 21.5 | Not recorded | 69d883f87d0172140ec7795d | | DS-R1-Distill-Qwen-7B | 13.1 | Not recorded | 69d883f87d0172140ec7795d | ### ReRec Performance (Simple): 67.1. Result ID: 69d8b15b47f34ce924c16ef0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### GRPO Performance (Simple): 66.4. Result ID: 69d8b15b47f34ce924c16eed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### REINFORCE++ Performance (Simple): 66.1. Result ID: 69d8b15b47f34ce924c16eee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### RLOO Performance (Simple): 66. Result ID: 69d8b15b47f34ce924c16eef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### RLOO Performance (Simple): 56.7. Result ID: 69d8b15b47f34ce924c16eeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Qwen-2.5-3B-Instruct"}. This record does not assert independent reproduction. ### TallRec Performance (Simple): 56.3. Result ID: 69d8b15b47f34ce924c16ee6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"LLM-based CRS"}. This record does not assert independent reproduction. ### GRPO Performance (Simple): 56.3. Result ID: 69d8b15b47f34ce924c16ee9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Qwen-2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Deepseek-R1 Performance (Simple): 56.2. Result ID: 69d8b15b47f34ce924c16ee5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"LLM Backbone"}. This record does not assert independent reproduction. ### CRAG Performance (Simple): 56. Result ID: 69d8b15b47f34ce924c16ee8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"LLM-based CRS"}. This record does not assert independent reproduction. ### InteRecAgent Performance (Simple): 55.7. Result ID: 69d8b15b47f34ce924c16ee7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"LLM-based CRS"}. This record does not assert independent reproduction. ### ReRec Performance (Simple): 55.5. Result ID: 69d8b15b47f34ce924c16eec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Qwen-2.5-3B-Instruct"}. This record does not assert independent reproduction. ### GPT-4o Performance (Simple): 55.4. Result ID: 69d8b15b47f34ce924c16ee4. [Reporting paper]() Recorded evaluation configuration: {"Category":"LLM Backbone"}. This record does not assert independent reproduction. ### REINFORCE++ Performance (Simple): 55.3. Result ID: 69d8b15b47f34ce924c16eea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RFT-trained Model","Base Model":"Qwen-2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Qwen-2.5-3B-Instruct Performance (Simple): 37.1. Result ID: 69d8b15b47f34ce924c16ee1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"LLM Backbone"}. This record does not assert independent reproduction. ### Llama-3.2-3B-Instruct Performance (Simple): 21.5. Result ID: 69d8b15b47f34ce924c16ee2. [Reporting paper]() Recorded evaluation configuration: {"Category":"LLM Backbone"}. This record does not assert independent reproduction. ### DS-R1-Distill-Qwen-7B Performance (Simple): 13.1. Result ID: 69d8b15b47f34ce924c16ee3. [Reporting paper]() Recorded evaluation configuration: {"Category":"LLM Backbone"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.