# Factual Accuracy and Reasoning on LoCoMo Source: [Factual Accuracy and Reasoning on LoCoMo]() Collection index: [llms.txt]() Data updated: 2026-05-26T11:58:26.090Z Evaluation of model performance on Factual Accuracy and Reasoning tasks using the LoCoMo dataset, broken down by Single-hop, Multi-hop, Open-domain, and Temporal 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 | Factual Accuracy and Reasoning | | Dataset (including any stated split) | LoCoMo | | Metric | Single-hop Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Single-hop Accuracy](): Higher is better; unit: PERCENT. - [Multi-hop Accuracy](): Higher is better; unit: PERCENT. - [Open-domain Accuracy](): Higher is better; unit: PERCENT. - [Temporal Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Single-hop Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Full-Context (Ceiling) | 88.53 | Not recorded | 69c0c8ea0636e5bf4afc3a76 | | Memori | 87.87 | Not recorded | 69c0c8ea0636e5bf4afc3a76 | | Zep | 79.43 | Not recorded | 69c0c8ea0636e5bf4afc3a76 | | LangMem | 74.47 | Not recorded | 69c0c8ea0636e5bf4afc3a76 | | Mem0 | 62.41 | Not recorded | 69c0c8ea0636e5bf4afc3a76 | | DUALMEM-RL | 41.8 | Not recorded | 6a15294adbd7150506f7e1c9 | | Qwen3 | 41.6 | Not recorded | 6a15294adbd7150506f7e1c9 | | DUALMEM-SFT | 40.3 | Not recorded | 6a15294adbd7150506f7e1c9 | | Qwen3 | 37.8 | Not recorded | 6a15294adbd7150506f7e1c9 | ### Full-Context (Ceiling) Single-hop Accuracy: 88.53. Result ID: 69c1261147f34ce924a9afa7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"source":"Du et al. \[2025\]"}. This record does not assert independent reproduction. ### Memori Single-hop Accuracy: 87.87. Result ID: 69c1261147f34ce924a9afa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"evaluation\_details":"Average of three rounds"}. This record does not assert independent reproduction. ### Zep Single-hop Accuracy: 79.43. Result ID: 69c1261147f34ce924a9afa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"source":"Du et al. \[2025\]"}. This record does not assert independent reproduction. ### LangMem Single-hop Accuracy: 74.47. Result ID: 69c1261147f34ce924a9afa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"source":"Du et al. \[2025\]"}. This record does not assert independent reproduction. ### Mem0 Single-hop Accuracy: 62.41. Result ID: 69c1261147f34ce924a9afa6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"source":"Du et al. \[2025\]"}. This record does not assert independent reproduction. ### DUALMEM-RL Single-hop Accuracy: 41.8. Result ID: 6a158adbfbc373592c0e1d94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"4B"}. This record does not assert independent reproduction. ### Qwen3 Single-hop Accuracy: 41.6. Result ID: 6a158adbfbc373592c0e1d92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"8B"}. This record does not assert independent reproduction. ### DUALMEM-SFT Single-hop Accuracy: 40.3. Result ID: 6a158adbfbc373592c0e1d93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"4B"}. This record does not assert independent reproduction. ### Qwen3 Single-hop Accuracy: 37.8. Result ID: 6a158adbfbc373592c0e1d91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"4B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.