# Long-term dialogue memory on PerLTQA (test) Source: [Long-term dialogue memory on PerLTQA (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:03.575Z Evaluation of model performance on the test split of the PerLTQA dataset specifically measuring long-term dialogue memory capabilities using accuracy metrics. 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 dialogue memory | | Dataset (including any stated split) | PerLTQA (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 | | --- | --- | --- | --- | | MemBuilder | 93.14 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 92.59 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 91.74 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 91.67 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 88.96 | Not recorded | 69647fe753fdd5c361744743 | | MIRIX | 83.11 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 82.19 | Not recorded | 69647fe753fdd5c361744743 | | RAG-Session | 79.21 | Not recorded | 69647fe753fdd5c361744743 | | RAG-Utterance | 77.23 | Not recorded | 69647fe753fdd5c361744743 | | MemBuilder | 76.85 | Not recorded | 69647fe753fdd5c361744743 | | Mem0 | 62.04 | Not recorded | 69647fe753fdd5c361744743 | ### MemBuilder Accuracy: 93.14. Result ID: 6996957d5698665ec4dedda2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"Qwen3-4B","Training stage":"SFT + RL","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 92.59. Result ID: 6996957d5698665ec4dedd9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"Claude 4.5 Sonnet","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 91.74. Result ID: 6996957d5698665ec4dedd9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"GPT-4.1","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 91.67. Result ID: 6996957d5698665ec4dedda0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"Qwen3-4B","Training stage":"SFT","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 88.96. Result ID: 6996957d5698665ec4dedd9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"QwQ-32B","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MIRIX Accuracy: 83.11. Result ID: 6996957d5698665ec4dedd9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction method":"Prompting-based","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 82.19. Result ID: 6996957d5698665ec4dedda1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"Qwen3-4B","Training stage":"RL","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### RAG-Session Accuracy: 79.21. Result ID: 6996957d5698665ec4dedd98. [Reporting paper]() Recorded evaluation configuration: {"Memory construction method":"Retrieval-based","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### RAG-Utterance Accuracy: 77.23. Result ID: 6996957d5698665ec4dedd99. [Reporting paper]() Recorded evaluation configuration: {"Memory construction method":"Retrieval-based","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### MemBuilder Accuracy: 76.85. Result ID: 6996957d5698665ec4dedd9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction model":"Qwen3-4B","Training stage":"Base","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 62.04. Result ID: 6996957d5698665ec4dedd9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Memory construction method":"Prompting-based","Answer model":"Claude 4.5 Sonnet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.