# Multi-hop retrieval question answering on HotPotQA (test) Source: [Multi-hop retrieval question answering on HotPotQA (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:56.231Z Evaluation of model performance on the test split of the HotPotQA dataset for multi-hop retrieval question answering, reporting Answer (Ans) and Passage (Psg) metrics. 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 retrieval question answering | | Dataset (including any stated split) | HotPotQA (test) | | Metric | Answer Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Answer Accuracy](): Higher is better; unit: PERCENT. - [Passage Retrieval Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Answer Accuracy | Result date | Report paper | | --- | --- | --- | --- | | multihop | 45.6 | Not recorded | 68fa70d01e209131cea4d60e | | multihop | 41 | Not recorded | 68fa70d01e209131cea4d60e | | multihop | 39.6 | Not recorded | 68fa70d01e209131cea4d60e | | multihop | 36.4 | Not recorded | 68fa70d01e209131cea4d60e | | COT\_RAG | 32.9 | Not recorded | 68fa70d01e209131cea4d60e | | vanilla | 31.5 | Not recorded | 68fa70d01e209131cea4d60e | | multihop | 31.3 | Not recorded | 68fa70d01e209131cea4d60e | | multihop | 31.2 | Not recorded | 68fa70d01e209131cea4d60e | | COT\_RAG | 29.8 | Not recorded | 68fa70d01e209131cea4d60e | | COT\_RAG | 28 | Not recorded | 68fa70d01e209131cea4d60e | | vanilla | 21.8 | Not recorded | 68fa70d01e209131cea4d60e | ### multihop Answer Accuracy: 45.6. Result ID: 69915ace3a6c31484907911e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-3.5","Compiler":"ensemble","eval\_subset":"50% of test set"}. This record does not assert independent reproduction. ### multihop Answer Accuracy: 41. Result ID: 69915ace3a6c314849079121. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"ensemble"}. This record does not assert independent reproduction. ### multihop Answer Accuracy: 39.6. Result ID: 69915ace3a6c31484907911d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-3.5","Compiler":"bootstrap"}. This record does not assert independent reproduction. ### multihop Answer Accuracy: 36.4. Result ID: 69915ace3a6c314849079120. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"bootstrap"}. This record does not assert independent reproduction. ### COT\_RAG Answer Accuracy: 32.9. Result ID: 69915ace3a6c31484907911b. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"bootstrap"}. This record does not assert independent reproduction. ### vanilla Answer Accuracy: 31.5. Result ID: 69915ace3a6c314849079117. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-3.5","Compiler":"fewshot"}. This record does not assert independent reproduction. ### multihop Answer Accuracy: 31.3. Result ID: 69915ace3a6c31484907911f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"fewshot"}. This record does not assert independent reproduction. ### multihop Answer Accuracy: 31.2. Result ID: 69915ace3a6c31484907911c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-3.5","Compiler":"fewshot"}. This record does not assert independent reproduction. ### COT\_RAG Answer Accuracy: 29.8. Result ID: 69915ace3a6c314849079119. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-3.5","Compiler":"fewshot"}. This record does not assert independent reproduction. ### COT\_RAG Answer Accuracy: 28. Result ID: 69915ace3a6c31484907911a. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"fewshot"}. This record does not assert independent reproduction. ### vanilla Answer Accuracy: 21.8. Result ID: 69915ace3a6c314849079118. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama2-13b-chat","Compiler":"fewshot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.