# Long-context Conversation Reasoning on LoCoMo Source: [Long-context Conversation Reasoning on LoCoMo]() Collection index: [llms.txt]() Data updated: 2026-05-18T09:08:27.714Z Evaluation of model performance on the LoCoMo dataset for long-context conversation reasoning, measured using Accuracy across Multi-Hop, Temporal, Open Domain, and Single-Hop sub-tasks, alongside token efficiency 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-context conversation reasoning | | Dataset (including any stated split) | LoCoMo | | Metric | Multi-Hop Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 Accuracy](): Higher is better; unit: PERCENT. - [Temporal Accuracy](): Higher is better; unit: PERCENT. - [Open Domain Accuracy](): Higher is better; unit: PERCENT. - [Single-Hop Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. - [Construct Token Count (K)](): Lower is better; unit: SCALAR. - [Query Token Count (K)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Multi-Hop Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FullContext | 82.62 | Not recorded | 6a0a9d31dbc836b87d82b52b | | RecMem | 78.37 | Not recorded | 6a0a9d31dbc836b87d82b52b | | RecMem | 72.7 | Not recorded | 6a0a9d31dbc836b87d82b52b | | FullContext | 69.86 | Not recorded | 6a0a9d31dbc836b87d82b52b | | MemoryOS | 66.31 | Not recorded | 6a0a9d31dbc836b87d82b52b | | A-Mem | 59.93 | Not recorded | 6a0a9d31dbc836b87d82b52b | | MemoryOS | 58.87 | Not recorded | 6a0a9d31dbc836b87d82b52b | | Naive RAG | 58.87 | Not recorded | 6a0a9d31dbc836b87d82b52b | | Mem0 | 58.16 | Not recorded | 6a0a9d31dbc836b87d82b52b | | Naive RAG | 54.61 | Not recorded | 6a0a9d31dbc836b87d82b52b | | Mem0 | 52.84 | Not recorded | 6a0a9d31dbc836b87d82b52b | | A-Mem | 52.13 | Not recorded | 6a0a9d31dbc836b87d82b52b | ### FullContext Multi-Hop Accuracy: 82.62. Result ID: 6a0ad63547f34ce924f12b7a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### RecMem Multi-Hop Accuracy: 78.37. Result ID: 6a0ad63547f34ce924f12b7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### RecMem Multi-Hop Accuracy: 72.7. Result ID: 6a0ad63547f34ce924f12b79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. ### FullContext Multi-Hop Accuracy: 69.86. Result ID: 6a0ad63547f34ce924f12b74. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. ### MemoryOS Multi-Hop Accuracy: 66.31. Result ID: 6a0ad63547f34ce924f12b7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### A-Mem Multi-Hop Accuracy: 59.93. Result ID: 6a0ad63547f34ce924f12b7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### MemoryOS Multi-Hop Accuracy: 58.87. Result ID: 6a0ad63547f34ce924f12b76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. ### Naive RAG Multi-Hop Accuracy: 58.87. Result ID: 6a0ad63547f34ce924f12b7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### Mem0 Multi-Hop Accuracy: 58.16. Result ID: 6a0ad63547f34ce924f12b7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4.1-MINI"}. This record does not assert independent reproduction. ### Naive RAG Multi-Hop Accuracy: 54.61. Result ID: 6a0ad63547f34ce924f12b75. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. ### Mem0 Multi-Hop Accuracy: 52.84. Result ID: 6a0ad63547f34ce924f12b77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. ### A-Mem Multi-Hop Accuracy: 52.13. Result ID: 6a0ad63547f34ce924f12b78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4O-MINI"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.