# Multi-hop Question Answering on HotpotQA subset of 100 questions Source: [Multi-hop Question Answering on HotpotQA subset of 100 questions]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:35.481Z Evaluation of model performance on the specific 100-question subset of the HotpotQA dataset for multi-hop question answering, typically measured using 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 subset of 100 questions | | Metric | EM | | 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 - [EM](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | LATS | 71 | Not recorded | 68fa738a1e209131cea5d15a | | LATS | 65 | Not recorded | 68fa738a1e209131cea5d15a | | LATS | 63 | Not recorded | 68fa738a1e209131cea5d15a | | LATS | 62 | Not recorded | 68fa738a1e209131cea5d15a | | RAP | 60 | Not recorded | 68fa738a1e209131cea5d15a | | RAP | 60 | Not recorded | 68fa738a1e209131cea5d15a | | LATS | 58 | Not recorded | 68fa738a1e209131cea5d15a | | ToT | 55 | Not recorded | 68fa738a1e209131cea5d15a | | RAP | 54 | Not recorded | 68fa738a1e209131cea5d15a | | Reflexion | 51 | Not recorded | 68fa738a1e209131cea5d15a | | ToT | 39 | Not recorded | 68fa738a1e209131cea5d15a | | CoT-SC | 38 | Not recorded | 68fa738a1e209131cea5d15a | | ReAct | 38 | Not recorded | 68fa738a1e209131cea5d15a | | CoT | 34 | Not recorded | 68fa738a1e209131cea5d15a | | Base LM | 32 | Not recorded | 68fa738a1e209131cea5d15a | | ReAct | 32 | Not recorded | 68fa738a1e209131cea5d15a | ### LATS EM: 71. Result ID: 6992f75e3a6c31484912babd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Method":"CoT + ReAct","Prompt Strategy":"Acting-based","Number of nodes (n)":5,"Number of trajectories (k)":50}. This record does not assert independent reproduction. ### LATS EM: 65. Result ID: 6992f75e3a6c31484912babc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Strategy":"Acting-based","Number of nodes (n)":10,"Number of trajectories (k)":50}. This record does not assert independent reproduction. ### LATS EM: 63. Result ID: 6992f75e3a6c31484912baba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Method":"ReAct","Prompt Strategy":"Acting-based","Number of nodes (n)":5,"Number of trajectories (k)":50}. This record does not assert independent reproduction. ### LATS EM: 62. Result ID: 6992f75e3a6c31484912baae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-3.5","Prompt Design":"CoT","n":5,"k":50}. This record does not assert independent reproduction. ### RAP EM: 60. Result ID: 6992f75e3a6c31484912baac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-3.5","k":50}. This record does not assert independent reproduction. ### RAP EM: 60. Result ID: 6992f75e3a6c31484912baad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-3.5","n":10}. This record does not assert independent reproduction. ### LATS EM: 58. Result ID: 6992f75e3a6c31484912babb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Strategy":"Acting-based","Number of nodes (n)":3,"Number of trajectories (k)":50}. This record does not assert independent reproduction. ### ToT EM: 55. Result ID: 6992f75e3a6c31484912baab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-3.5","Search Algorithm":"DFS","k":50}. This record does not assert independent reproduction. ### RAP EM: 54. Result ID: 6992f75e3a6c31484912bab9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Method":"ReAct","Prompt Strategy":"Acting-based"}. This record does not assert independent reproduction. ### Reflexion EM: 51. Result ID: 6992f75e3a6c31484912bab7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Strategy":"Acting-based"}. This record does not assert independent reproduction. ### ToT EM: 39. Result ID: 6992f75e3a6c31484912bab8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Method":"ReAct","Prompt Strategy":"Acting-based"}. This record does not assert independent reproduction. ### CoT-SC EM: 38. Result ID: 6992f75e3a6c31484912baaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-3.5"}. This record does not assert independent reproduction. ### ReAct EM: 38. Result ID: 6992f75e3a6c31484912bab6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Strategy":"Acting-based","selection":"best of k","Number of trajectories (k)":50}. This record does not assert independent reproduction. ### CoT EM: 34. Result ID: 6992f75e3a6c31484912baa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-3.5"}. This record does not assert independent reproduction. ### Base LM EM: 32. Result ID: 6992f75e3a6c31484912baa8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-3.5"}. This record does not assert independent reproduction. ### ReAct EM: 32. Result ID: 6992f75e3a6c31484912bab5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GPT-3.5","Prompt Strategy":"Acting-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.