# Personalized Prediction on MovieLens (test) Source: [Personalized Prediction on MovieLens (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:50.674Z Evaluation of Personalized Prediction performance on the test split of the MovieLens dataset, measured using Accuracy. 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 Prediction | | Dataset (including any stated split) | MovieLens (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Attn-G | 0.646 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Attn-G | 0.618 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Mark ALL | 0.599 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Direct Summary | 0.598 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Prompt-G | 0.596 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Self-Reflection | 0.596 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | CoT | 0.595 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Random Mark | 0.594 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Attn-G | 0.59 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Mark ALL | 0.586 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Direct Summary | 0.584 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Self-Reflection | 0.583 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Prompt-G | 0.582 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Attn-G | 0.582 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Truncate | 0.581 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | CoT | 0.581 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Random Mark | 0.58 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Mark ALL | 0.573 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Direct Summary | 0.571 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Self-Reflection | 0.57 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Prompt-G | 0.569 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | CoT | 0.568 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Random Mark | 0.567 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Mark ALL | 0.564 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Direct Summary | 0.562 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Self-Reflection | 0.561 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Truncate | 0.56 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Prompt-G | 0.56 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | CoT | 0.559 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Random Mark | 0.558 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Truncate | 0.54 | Not recorded | 698abbffc97a0b3e3b5de2e4 | | Truncate | 0.526 | Not recorded | 698abbffc97a0b3e3b5de2e4 | ### Attn-G Accuracy: 0.646. Result ID: 6996428b5698665ec4862019. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Attn-G Accuracy: 0.618. Result ID: 6996428b5698665ec4862018. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Mark ALL Accuracy: 0.599. Result ID: 6996428b5698665ec4862009. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Direct Summary Accuracy: 0.598. Result ID: 6996428b5698665ec4862001. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Prompt-G Accuracy: 0.596. Result ID: 6996428b5698665ec486200d. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Self-Reflection Accuracy: 0.596. Result ID: 6996428b5698665ec4862015. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### CoT Accuracy: 0.595. Result ID: 6996428b5698665ec4862011. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Random Mark Accuracy: 0.594. Result ID: 6996428b5698665ec4862005. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Attn-G Accuracy: 0.59. Result ID: 6996428b5698665ec4862017. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Mark ALL Accuracy: 0.586. Result ID: 6996428b5698665ec4862008. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Direct Summary Accuracy: 0.584. Result ID: 6996428b5698665ec4862000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Self-Reflection Accuracy: 0.583. Result ID: 6996428b5698665ec4862014. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Prompt-G Accuracy: 0.582. Result ID: 6996428b5698665ec486200c. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Attn-G Accuracy: 0.582. Result ID: 6996428b5698665ec4862016. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Truncate Accuracy: 0.581. Result ID: 6996428b5698665ec4861ffd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"200","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### CoT Accuracy: 0.581. Result ID: 6996428b5698665ec4862010. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Random Mark Accuracy: 0.58. Result ID: 6996428b5698665ec4862004. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Mark ALL Accuracy: 0.573. Result ID: 6996428b5698665ec4862007. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Direct Summary Accuracy: 0.571. Result ID: 6996428b5698665ec4861fff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Self-Reflection Accuracy: 0.57. Result ID: 6996428b5698665ec4862013. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Prompt-G Accuracy: 0.569. Result ID: 6996428b5698665ec486200b. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### CoT Accuracy: 0.568. Result ID: 6996428b5698665ec486200f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Random Mark Accuracy: 0.567. Result ID: 6996428b5698665ec4862003. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Mark ALL Accuracy: 0.564. Result ID: 6996428b5698665ec4862006. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Direct Summary Accuracy: 0.562. Result ID: 6996428b5698665ec4861ffe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Self-Reflection Accuracy: 0.561. Result ID: 6996428b5698665ec4862012. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Truncate Accuracy: 0.56. Result ID: 6996428b5698665ec4861ffc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"150","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Prompt-G Accuracy: 0.56. Result ID: 6996428b5698665ec486200a. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### CoT Accuracy: 0.559. Result ID: 6996428b5698665ec486200e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Random Mark Accuracy: 0.558. Result ID: 6996428b5698665ec4862002. [Reporting paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Truncate Accuracy: 0.54. Result ID: 6996428b5698665ec4861ffb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"100","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. ### Truncate Accuracy: 0.526. Result ID: 6996428b5698665ec4861ffa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Token Count":"50","Backbone":"Llama-1B-FT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.