# Long-context Question Answering on LoCoMo (test) Source: [Long-context Question Answering on LoCoMo (test)]() Collection index: [llms.txt]() Data updated: 2026-07-02T07:33:29.447Z Evaluation of Long-context Question Answering performance on the LoCoMo test set, reporting LLM, F1, and BLEU scores across Temporal, Open Domain, Multi-Hop, and Single-Hop question types. 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 Question Answering | | Dataset (including any stated split) | LoCoMo (test) | | Metric | LLM Score (Temporal) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [LLM Score (Temporal)](): Higher is better; unit: PERCENT. - [F1 Score (Temporal)](): Higher is better; unit: PERCENT. - [BLEU Score (Temporal)](): Higher is better; unit: PERCENT. - [LLM Score (Open Domain)](): Higher is better; unit: PERCENT. - [F1 Score (Open Domain)](): Higher is better; unit: PERCENT. - [BLEU Score (Open Domain)](): Higher is better; unit: PERCENT. - [LLM Score (Multi-Hop)](): Higher is better; unit: PERCENT. - [F1 Score (Multi-Hop)](): Higher is better; unit: PERCENT. - [BLEU Score (Multi-Hop)](): Higher is better; unit: PERCENT. - [LLM Score (Single-Hop)](): Higher is better; unit: PERCENT. - [F1 Score (Single-Hop)](): Higher is better; unit: PERCENT. - [BLEU Score (Single-Hop)](): Higher is better; unit: PERCENT. - [LLM Score (Overall)](): Higher is better; unit: PERCENT. - [F1 Score (Overall)](): Higher is better; unit: PERCENT. - [BLEU Score (Overall)](): Higher is better; unit: PERCENT. ## Recorded results | Method | LLM Score (Temporal) | Result date | Report paper | | --- | --- | --- | --- | | TRACE | 72.3 | Not recorded | 6a45f084dc71372d7795a209 | | TRACE | 69.3 | Not recorded | 6a45f084dc71372d7795a209 | | Zep | 66 | Not recorded | 6a45f084dc71372d7795a209 | | Nemori | 62.1 | Not recorded | 6a45f084dc71372d7795a209 | | Mem0 | 57.7 | Not recorded | 6a45f084dc71372d7795a209 | | Full-Context | 52.4 | Not recorded | 6a45f084dc71372d7795a209 | | Nemori | 50.7 | Not recorded | 6a45f084dc71372d7795a209 | | A-Mem | 49.4 | Not recorded | 6a45f084dc71372d7795a209 | | RAG | 46.2 | Not recorded | 6a45f084dc71372d7795a209 | | A-Mem | 46.2 | Not recorded | 6a45f084dc71372d7795a209 | | Full-Context | 43.5 | Not recorded | 6a45f084dc71372d7795a209 | | RAG | 43.5 | Not recorded | 6a45f084dc71372d7795a209 | | LangMem | 35.1 | Not recorded | 6a45f084dc71372d7795a209 | | Zep | 33.1 | Not recorded | 6a45f084dc71372d7795a209 | | Mem0 | 28.8 | Not recorded | 6a45f084dc71372d7795a209 | | LangMem | 21.5 | Not recorded | 6a45f084dc71372d7795a209 | ### TRACE LLM Score (Temporal): 72.3. Result ID: 6a46142c60b88bb3398422c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### TRACE LLM Score (Temporal): 69.3. Result ID: 6a46142c60b88bb3398422b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Zep LLM Score (Temporal): 66. Result ID: 6a46142c60b88bb3398422bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Nemori LLM Score (Temporal): 62.1. Result ID: 6a46142c60b88bb3398422be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Mem0 LLM Score (Temporal): 57.7. Result ID: 6a46142c60b88bb3398422bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Full-Context LLM Score (Temporal): 52.4. Result ID: 6a46142c60b88bb3398422b9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Nemori LLM Score (Temporal): 50.7. Result ID: 6a46142c60b88bb3398422b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### A-Mem LLM Score (Temporal): 49.4. Result ID: 6a46142c60b88bb3398422b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### RAG LLM Score (Temporal): 46.2. Result ID: 6a46142c60b88bb3398422b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### A-Mem LLM Score (Temporal): 46.2. Result ID: 6a46142c60b88bb3398422bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Full-Context LLM Score (Temporal): 43.5. Result ID: 6a46142c60b88bb3398422b1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### RAG LLM Score (Temporal): 43.5. Result ID: 6a46142c60b88bb3398422ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### LangMem LLM Score (Temporal): 35.1. Result ID: 6a46142c60b88bb3398422bb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash"}. This record does not assert independent reproduction. ### Zep LLM Score (Temporal): 33.1. Result ID: 6a46142c60b88bb3398422b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Mem0 LLM Score (Temporal): 28.8. Result ID: 6a46142c60b88bb3398422b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### LangMem LLM Score (Temporal): 21.5. Result ID: 6a46142c60b88bb3398422b3. [Reporting 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.