# Multi-hop Question Answering on HotpotQA 400 documents Source: [Multi-hop Question Answering on HotpotQA 400 documents]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:29.828Z Evaluation of model performance on the HotpotQA dataset subset consisting of exactly 400 documents, focusing on multi-hop question answering capabilities. 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 400 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 | 61.46 | Not recorded | 697c3b5da8b01e76cc8da676 | | E-mem | 61.13 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 56.56 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 54.75 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 52.71 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 51.81 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 49.75 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 48.4 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 40.93 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 37.3 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 33.9 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 32.85 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 30.12 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 27.04 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 26.47 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 24.58 | Not recorded | 697c3b5da8b01e76cc8da676 | ### E-mem F1 Score: 61.46. Result ID: 6996184c5698665ec4581ae5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### E-mem F1 Score: 61.13. Result ID: 6996184c5698665ec4581aed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Long-Context F1 Score: 56.56. Result ID: 6996184c5698665ec4581ade. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### GAM F1 Score: 54.75. Result ID: 6996184c5698665ec4581ae4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### RAG F1 Score: 52.71. Result ID: 6996184c5698665ec4581adf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### RAG F1 Score: 51.81. Result ID: 6996184c5698665ec4581ae7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Long-Context F1 Score: 49.75. Result ID: 6996184c5698665ec4581ae6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### GAM F1 Score: 48.4. Result ID: 6996184c5698665ec4581aec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### LIGHTMEM F1 Score: 40.93. Result ID: 6996184c5698665ec4581ae3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### LIGHTMEM F1 Score: 37.3. Result ID: 6996184c5698665ec4581aeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1 Score: 33.9. Result ID: 6996184c5698665ec4581ae0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Mem0 F1 Score: 32.85. Result ID: 6996184c5698665ec4581ae1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Mem0 F1 Score: 30.12. Result ID: 6996184c5698665ec4581ae9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1 Score: 27.04. Result ID: 6996184c5698665ec4581ae8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### MEMORYOS F1 Score: 26.47. Result ID: 6996184c5698665ec4581ae2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### MEMORYOS F1 Score: 24.58. Result ID: 6996184c5698665ec4581aea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.