# Multi-hop Question Answering on HotpotQA 1600 documents Source: [Multi-hop Question Answering on HotpotQA 1600 documents]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:46.588Z Evaluation of model performance on the HotpotQA dataset subset consisting of exactly 1600 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 1600 documents | | Metric | F1 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 | Result date | Report paper | | --- | --- | --- | --- | | E-mem | 55.76 | Not recorded | 697c3b5da8b01e76cc8da676 | | E-mem | 54.87 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 54.01 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 53.92 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 53.71 | Not recorded | 697c3b5da8b01e76cc8da676 | | RAG | 48.36 | Not recorded | 697c3b5da8b01e76cc8da676 | | GAM | 44.32 | Not recorded | 697c3b5da8b01e76cc8da676 | | Long-Context | 43.17 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 31.37 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 30.02 | Not recorded | 697c3b5da8b01e76cc8da676 | | LIGHTMEM | 28.25 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 27.41 | Not recorded | 697c3b5da8b01e76cc8da676 | | Mem0 | 26.55 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 24.16 | Not recorded | 697c3b5da8b01e76cc8da676 | | MEMORYOS | 23.13 | Not recorded | 697c3b5da8b01e76cc8da676 | | A-mem | 22.92 | Not recorded | 697c3b5da8b01e76cc8da676 | ### E-mem F1: 55.76. Result ID: 6996184c5698665ec4581b05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### E-mem F1: 54.87. Result ID: 6996184c5698665ec4581b0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### RAG F1: 54.01. Result ID: 6996184c5698665ec4581aff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Long-Context F1: 53.92. Result ID: 6996184c5698665ec4581afe. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### GAM F1: 53.71. Result ID: 6996184c5698665ec4581b04. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### RAG F1: 48.36. Result ID: 6996184c5698665ec4581b07. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### GAM F1: 44.32. Result ID: 6996184c5698665ec4581b0c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Long-Context F1: 43.17. Result ID: 6996184c5698665ec4581b06. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1: 31.37. Result ID: 6996184c5698665ec4581b00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### LIGHTMEM F1: 30.02. Result ID: 6996184c5698665ec4581b03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### LIGHTMEM F1: 28.25. Result ID: 6996184c5698665ec4581b0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### Mem0 F1: 27.41. Result ID: 6996184c5698665ec4581b01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### Mem0 F1: 26.55. Result ID: 6996184c5698665ec4581b09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### MEMORYOS F1: 24.16. Result ID: 6996184c5698665ec4581b02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4o-mini"}. This record does not assert independent reproduction. ### MEMORYOS F1: 23.13. Result ID: 6996184c5698665ec4581b0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B"}. This record does not assert independent reproduction. ### A-mem F1: 22.92. Result ID: 6996184c5698665ec4581b08. [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.