# Long-term Memory Question Answering on REALTALK (Overall) Source: [Long-term Memory Question Answering on REALTALK (Overall)]() Collection index: [llms.txt]() Data updated: 2026-05-18T08:08:03.451Z Evaluation of long-term memory question answering capabilities on the REALTALK dataset, focusing on performance across multi-hop reasoning, temporal consistency, and open-domain recall. 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 | Long-term Memory Question Answering | | Dataset (including any stated split) | REALTALK (Overall) | | Metric | Multi-hop F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Multi-hop F1](): Higher is better; unit: PERCENT. - [Multi-hop Accuracy](): Higher is better; unit: PERCENT. - [Temporal F1](): Higher is better; unit: PERCENT. - [Temporal Accuracy](): Higher is better; unit: PERCENT. - [Open-domain F1](): Higher is better; unit: PERCENT. - [Open-domain Accuracy](): Higher is better; unit: PERCENT. - [Overall F1](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Multi-hop F1 | Result date | Report paper | | --- | --- | --- | --- | | H-MEM | 37.41 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | EverMemOS | 35.78 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | MemTree | 31.18 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | MemOS | 30.66 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | Mem0 | 28.44 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | Zep | 28.15 | Not recorded | 6a0a9cdfdbc836b87d82b249 | | MemoryOS | 26.83 | Not recorded | 6a0a9cdfdbc836b87d82b249 | ### H-MEM Multi-hop F1: 37.41. Result ID: 6a0ac78f47f34ce924f0b85c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EverMemOS Multi-hop F1: 35.78. Result ID: 6a0ac78f47f34ce924f0b85b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MemTree Multi-hop F1: 31.18. Result ID: 6a0ac78f47f34ce924f0b858. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MemOS Multi-hop F1: 30.66. Result ID: 6a0ac78f47f34ce924f0b859. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mem0 Multi-hop F1: 28.44. Result ID: 6a0ac78f47f34ce924f0b857. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zep Multi-hop F1: 28.15. Result ID: 6a0ac78f47f34ce924f0b85a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MemoryOS Multi-hop F1: 26.83. Result ID: 6a0ac78f47f34ce924f0b856. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.