# Multi-hop Question Answering on HotpotQA (F1, EM) Source: [Multi-hop Question Answering on HotpotQA (F1, EM)]() Collection index: [llms.txt]() Data updated: 2026-04-28T10:26:54.089Z Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting standard F1 score and Exact Match (EM). 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 | | Metric | F1 Score | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [EM Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | SEARCH-R | 61.63 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | SEARCH-R | 60.06 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | ChainRAG | 59.13 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | Iter-RetGen | 57.77 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | NativeRAG | 56.92 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | HippoRAG | 56.12 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | ChainRAG | 53.99 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | SEARCH-R | 49.09 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | NativeRAG | 47 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | NativeRAG | 46.19 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | ChainRAG | 45.21 | Not recorded | 69f03f7f55a3c32af89fa5b4 | | Search-R1 | 43.52 | Not recorded | 69f03f7f55a3c32af89fa5b4 | ### SEARCH-R F1 Score: 61.63. Result ID: 69f08b5a47f34ce924d72a7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B+DeepSeek-V3"}. This record does not assert independent reproduction. ### SEARCH-R F1 Score: 60.06. Result ID: 69f08b5a47f34ce924d72a82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B+GPT-4o-mini"}. This record does not assert independent reproduction. ### ChainRAG F1 Score: 59.13. Result ID: 69f08b5a47f34ce924d72a81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Iter-RetGen F1 Score: 57.77. Result ID: 69f08b5a47f34ce924d72a7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### NativeRAG F1 Score: 56.92. Result ID: 69f08b5a47f34ce924d72a7e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### HippoRAG F1 Score: 56.12. Result ID: 69f08b5a47f34ce924d72a80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction. ### ChainRAG F1 Score: 53.99. Result ID: 69f08b5a47f34ce924d72a7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction. ### SEARCH-R F1 Score: 49.09. Result ID: 69f08b5a47f34ce924d72a7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### NativeRAG F1 Score: 47. Result ID: 69f08b5a47f34ce924d72a77. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### NativeRAG F1 Score: 46.19. Result ID: 69f08b5a47f34ce924d72a7b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction. ### ChainRAG F1 Score: 45.21. Result ID: 69f08b5a47f34ce924d72a79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Search-R1 F1 Score: 43.52. Result ID: 69f08b5a47f34ce924d72a78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.