# Multi-hop Question Answering on Bamboogle (EM, LJ) Source: [Multi-hop Question Answering on Bamboogle (EM, LJ)]() Collection index: [llms.txt]() Data updated: 2026-05-29T07:53:15.032Z Evaluation of model performance on the Bamboogle dataset for Multi-hop Question Answering, reporting Exact Match (EM) and LJ scores. 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) | Bamboogle | | 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. - [LJ Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | M2R | 44.56 | Not recorded | 6a191d5fdbd7150506f82627 | | ReSearch | 42.4 | Not recorded | 6a191d5fdbd7150506f82627 | | M2R | 39.58 | Not recorded | 6a191d5fdbd7150506f82627 | | SURE | 39.58 | Not recorded | 6a191d5fdbd7150506f82627 | | ReSearch | 38.11 | Not recorded | 6a191d5fdbd7150506f82627 | | COFT | 35.71 | Not recorded | 6a191d5fdbd7150506f82627 | | SURE | 31.2 | Not recorded | 6a191d5fdbd7150506f82627 | | COFT | 25.3 | Not recorded | 6a191d5fdbd7150506f82627 | | IRCoT | 24.8 | Not recorded | 6a191d5fdbd7150506f82627 | | Iter-RetGen | 21.6 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive RAG | 20.8 | Not recorded | 6a191d5fdbd7150506f82627 | | IRCoT | 17.6 | Not recorded | 6a191d5fdbd7150506f82627 | | Iter-RetGen | 16.03 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive RAG | 14.43 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive Generation | 10.4 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive Generation | 5.01 | Not recorded | 6a191d5fdbd7150506f82627 | ### M2R EM: 44.56. Result ID: 6a1945defbc373592c136bea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ReSearch EM: 42.4. Result ID: 6a1945defbc373592c136be9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### M2R EM: 39.58. Result ID: 6a1945defbc373592c136be2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### SURE EM: 39.58. Result ID: 6a1945defbc373592c136be8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ReSearch EM: 38.11. Result ID: 6a1945defbc373592c136be1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### COFT EM: 35.71. Result ID: 6a1945defbc373592c136be7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### SURE EM: 31.2. Result ID: 6a1945defbc373592c136be0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### COFT EM: 25.3. Result ID: 6a1945defbc373592c136bdf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### IRCoT EM: 24.8. Result ID: 6a1945defbc373592c136be6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Iter-RetGen EM: 21.6. Result ID: 6a1945defbc373592c136be5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Naive RAG EM: 20.8. Result ID: 6a1945defbc373592c136be4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### IRCoT EM: 17.6. Result ID: 6a1945defbc373592c136bde. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Iter-RetGen EM: 16.03. Result ID: 6a1945defbc373592c136bdd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Naive RAG EM: 14.43. Result ID: 6a1945defbc373592c136bdc. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Naive Generation EM: 10.4. Result ID: 6a1945defbc373592c136be3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Naive Generation EM: 5.01. Result ID: 6a1945defbc373592c136bdb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.