# Multi-hop Question Answering on HotpotQA 800 documents Source: [Multi-hop Question Answering on HotpotQA 800 documents]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:29.842Z Evaluation of model performance on the HotpotQA dataset subset consisting of 800 documents, focusing on multi-hop question answering. 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 | Multi-hop Question Answering | | Dataset (including any stated split) | HotpotQA 800 documents | | Metric | F1 Score | | 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 - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | E-mem | 55.46 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 52.86 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 51.84 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 49.71 | Not recorded | 697c3b5da8b01e76cc8da676 | | E-mem | 47.91 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 46.82 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 46.72 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 41.1 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 35.28 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 32.44 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 31.74 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 30.25 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 30.2 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 27.72 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 25.65 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 23.1 | Not recorded | 697c3b5da8b01e76cc8da676 | ### E-mem F1 Score: 55.46. Result ID: 6996184c5698665ec4581af5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### GAM F1 Score: 52.86. Result ID: 6996184c5698665ec4581af4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### RAG F1 Score: 51.84. Result ID: 6996184c5698665ec4581aef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Long-Context F1 Score: 49.71. Result ID: 6996184c5698665ec4581aee. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### E-mem F1 Score: 47.91. Result ID: 6996184c5698665ec4581afd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Long-Context F1 Score: 46.82. Result ID: 6996184c5698665ec4581af6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### RAG F1 Score: 46.72. Result ID: 6996184c5698665ec4581af7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### GAM F1 Score: 41.1. Result ID: 6996184c5698665ec4581afc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### LIGHTMEM F1 Score: 35.28. Result ID: 6996184c5698665ec4581af3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Mem0 F1 Score: 32.44. Result ID: 6996184c5698665ec4581af9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Mem0 F1 Score: 31.74. Result ID: 6996184c5698665ec4581af1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### MEMORYOS F1 Score: 30.25. Result ID: 6996184c5698665ec4581afa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1 Score: 30.2. Result ID: 6996184c5698665ec4581af0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### LIGHTMEM F1 Score: 27.72. Result ID: 6996184c5698665ec4581afb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1 Score: 25.65. Result ID: 6996184c5698665ec4581af8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### MEMORYOS F1 Score: 23.1. Result ID: 6996184c5698665ec4581af2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.