# Simple Retrieval on Ruler S-NIAH Source: [Simple Retrieval on Ruler S-NIAH]() Collection index: [llms.txt]() Data updated: 2026-03-04T19:24:41.243Z Evaluation of simple retrieval performance on the Ruler S-NIAH 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 | Simple Retrieval | | Dataset (including any stated split) | Ruler S-NIAH | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GPT-5 | 100 | Not recorded | 69a7bc982d603e6de3e3d675 | | RLM | 100 | Not recorded | 69a7bc982d603e6de3e3d675 | | DeepSeek v3.2 | 100 | Not recorded | 69a7bc982d603e6de3e3d675 | | Kimi K2 | 100 | Not recorded | 69a7bc982d603e6de3e3d675 | | RLM | 90 | Not recorded | 69a7bc982d603e6de3e3d675 | | RLM | 90 | Not recorded | 69a7bc982d603e6de3e3d675 | | RLM | 85 | Not recorded | 69a7bc982d603e6de3e3d675 | | RLM | 70 | Not recorded | 69a7bc982d603e6de3e3d675 | ### GPT-5 Accuracy: 100. Result ID: 69a886df6dbb7075b950f8c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Base LLM"}. This record does not assert independent reproduction. ### RLM Accuracy: 100. Result ID: 69a886df6dbb7075b950f8c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5","Recursion Depth":"1"}. This record does not assert independent reproduction. ### DeepSeek v3.2 Accuracy: 100. Result ID: 69a886df6dbb7075b950f8c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"Base LLM"}. This record does not assert independent reproduction. ### Kimi K2 Accuracy: 100. Result ID: 69a886df6dbb7075b950f8cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"Base LLM"}. This record does not assert independent reproduction. ### RLM Accuracy: 90. Result ID: 69a886df6dbb7075b950f8cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Kimi K2","Recursion Depth":"1"}. This record does not assert independent reproduction. ### RLM Accuracy: 90. Result ID: 69a886df6dbb7075b950f8cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Kimi K2","Recursion Depth":"2"}. This record does not assert independent reproduction. ### RLM Accuracy: 85. Result ID: 69a886df6dbb7075b950f8c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek v3.2","Recursion Depth":"1"}. This record does not assert independent reproduction. ### RLM Accuracy: 70. Result ID: 69a886df6dbb7075b950f8ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek v3.2","Recursion Depth":"2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.