# Multi-hop Question Answering on HotpotQA (F1, Latency) Source: [Multi-hop Question Answering on HotpotQA (F1, Latency)]() Collection index: [llms.txt]() Data updated: 2026-05-14T09:46:00.833Z Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, focusing on F1 score and inference latency. 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 | 8 of 8 | | 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. - [Latency (s)](): Lower is better; unit: TIME. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | FlowCompile | 86.69 | Not recorded | 6a055728dbc836b87d828d91 | | Qwen3-8B | 86.58 | Not recorded | 6a055728dbc836b87d828d91 | | Full Baseline | 86.29 | Not recorded | 6a055728dbc836b87d828d91 | | FlowCompile | 85.32 | Not recorded | 6a055728dbc836b87d828d91 | | Qwen3-4B | 83.89 | Not recorded | 6a055728dbc836b87d828d91 | | MaAS | 83.44 | Not recorded | 6a055728dbc836b87d828d91 | | KNN Router | 73.75 | Not recorded | 6a055728dbc836b87d828d91 | | MaAS | 71.82 | Not recorded | 6a055728dbc836b87d828d91 | ### FlowCompile F1 Score: 86.69. Result ID: 6a05999347f34ce924ed091b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Selection Priority":"Accuracy-priority"}. This record does not assert independent reproduction. ### Qwen3-8B F1 Score: 86.58. Result ID: 6a05999347f34ce924ed0917. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Full Baseline F1 Score: 86.29. Result ID: 6a05999347f34ce924ed0915. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction. ### FlowCompile F1 Score: 85.32. Result ID: 6a05999347f34ce924ed091c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Selection Priority":"Latency-priority"}. This record does not assert independent reproduction. ### Qwen3-4B F1 Score: 83.89. Result ID: 6a05999347f34ce924ed0916. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### MaAS F1 Score: 83.44. Result ID: 6a05999347f34ce924ed0919. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### KNN Router F1 Score: 73.75. Result ID: 6a05999347f34ce924ed091a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MaAS F1 Score: 71.82. Result ID: 6a05999347f34ce924ed0918. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.