# Multimodal Personalized Question Answering on LoCoMo (test) Source: [Multimodal Personalized Question Answering on LoCoMo (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:52:58.424Z Evaluation of model performance on the test split of the LoCoMo dataset for Multimodal Personalized Question Answering. Metrics are reported across various question types including Multi Hop, Temporal, Open Domain, Single Hop, and Visual, providing Query (Q), Ground Truth (G), and Average (Avg) scores. 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 | Multimodal Personalized Question Answering | | Dataset (including any stated split) | LoCoMo (test) | | Metric | Multi Hop (Q) | | 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 (Q)](): Higher is better; unit: PERCENT. - [Multi Hop (G)](): Higher is better; unit: PERCENT. - [Multi Hop (Avg)](): Higher is better; unit: PERCENT. - [Temporal (Q)](): Higher is better; unit: PERCENT. - [Temporal (G)](): Higher is better; unit: PERCENT. - [Temporal (Avg)](): Higher is better; unit: PERCENT. - [Open Domain (Q)](): Higher is better; unit: PERCENT. - [Open Domain (G)](): Higher is better; unit: PERCENT. - [Open Domain (Avg)](): Higher is better; unit: PERCENT. - [Single Hop (Q)](): Higher is better; unit: PERCENT. - [Single Hop (G)](): Higher is better; unit: PERCENT. - [Single Hop (Avg)](): Higher is better; unit: PERCENT. - [Visual (Q)](): Higher is better; unit: PERCENT. - [Visual (G)](): Higher is better; unit: PERCENT. - [Visual (Avg)](): Higher is better; unit: PERCENT. - [Total (Q)](): Higher is better; unit: PERCENT. - [Total (G)](): Higher is better; unit: PERCENT. - [Total (Avg)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Multi Hop (Q) | Result date | Report paper | | --- | --- | --- | --- | | M2A | 48.58 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | Mem0 | 43.97 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | M2A | 43.26 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | A-MEM | 41.84 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | A-MEM | 40.07 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | Mem0 | 34.75 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | A-MEM | 28.36 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | M2A | 27.3 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | LoCoMo | 27.1 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | Mem0 | 25.89 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | LoCoMo | 25.18 | Not recorded | 698abb82c97a0b3e3b5ddf58 | | LoCoMo | 24.82 | Not recorded | 698abb82c97a0b3e3b5ddf58 | ### M2A Multi Hop (Q): 48.58. Result ID: 6995fda45698665ec4333533. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6V Flash"}. This record does not assert independent reproduction. ### Mem0 Multi Hop (Q): 43.97. Result ID: 6995fda45698665ec4333531. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6V Flash"}. This record does not assert independent reproduction. ### M2A Multi Hop (Q): 43.26. Result ID: 6995fda45698665ec433352f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3VL 8b"}. This record does not assert independent reproduction. ### A-MEM Multi Hop (Q): 41.84. Result ID: 6995fda45698665ec4333532. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6V Flash"}. This record does not assert independent reproduction. ### A-MEM Multi Hop (Q): 40.07. Result ID: 6995fda45698665ec433352e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3VL 8b"}. This record does not assert independent reproduction. ### Mem0 Multi Hop (Q): 34.75. Result ID: 6995fda45698665ec433352d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3VL 8b"}. This record does not assert independent reproduction. ### A-MEM Multi Hop (Q): 28.36. Result ID: 6995fda45698665ec433352a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### M2A Multi Hop (Q): 27.3. Result ID: 6995fda45698665ec433352b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### LoCoMo Multi Hop (Q): 27.1. Result ID: 6995fda45698665ec4333528. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Mem0 Multi Hop (Q): 25.89. Result ID: 6995fda45698665ec4333529. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### LoCoMo Multi Hop (Q): 25.18. Result ID: 6995fda45698665ec4333530. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6V Flash"}. This record does not assert independent reproduction. ### LoCoMo Multi Hop (Q): 24.82. Result ID: 6995fda45698665ec433352c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3VL 8b"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.