# Multi-hop Question Answering on MuSiQue (EM, LJ) Source: [Multi-hop Question Answering on MuSiQue (EM, LJ)]() Collection index: [llms.txt]() Data updated: 2026-05-29T07:53:15.001Z Evaluation of model performance on the MuSiQue 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) | MuSiQue | | 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 | 24.12 | Not recorded | 6a191d5fdbd7150506f82627 | | ReSearch | 22.3 | Not recorded | 6a191d5fdbd7150506f82627 | | M2R | 20.87 | Not recorded | 6a191d5fdbd7150506f82627 | | SURE | 20.87 | Not recorded | 6a191d5fdbd7150506f82627 | | ReSearch | 19.4 | Not recorded | 6a191d5fdbd7150506f82627 | | SURE | 17.24 | Not recorded | 6a191d5fdbd7150506f82627 | | COFT | 17.12 | Not recorded | 6a191d5fdbd7150506f82627 | | COFT | 13.49 | Not recorded | 6a191d5fdbd7150506f82627 | | Iter-RetGen | 8.69 | Not recorded | 6a191d5fdbd7150506f82627 | | IRCoT | 6.99 | Not recorded | 6a191d5fdbd7150506f82627 | | Iter-RetGen | 6.91 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive RAG | 6.21 | Not recorded | 6a191d5fdbd7150506f82627 | | IRCoT | 4.39 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive RAG | 4.14 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive Generation | 3.76 | Not recorded | 6a191d5fdbd7150506f82627 | | Naive Generation | 2.62 | Not recorded | 6a191d5fdbd7150506f82627 | ### M2R EM: 24.12. Result ID: 6a1945defbc373592c136bda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ReSearch EM: 22.3. Result ID: 6a1945defbc373592c136bd9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### M2R EM: 20.87. Result ID: 6a1945defbc373592c136bd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### SURE EM: 20.87. Result ID: 6a1945defbc373592c136bd8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ReSearch EM: 19.4. Result ID: 6a1945defbc373592c136bd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### SURE EM: 17.24. Result ID: 6a1945defbc373592c136bd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### COFT EM: 17.12. Result ID: 6a1945defbc373592c136bd7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### COFT EM: 13.49. Result ID: 6a1945defbc373592c136bcf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Iter-RetGen EM: 8.69. Result ID: 6a1945defbc373592c136bd5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### IRCoT EM: 6.99. Result ID: 6a1945defbc373592c136bd6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Iter-RetGen EM: 6.91. Result ID: 6a1945defbc373592c136bcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Naive RAG EM: 6.21. Result ID: 6a1945defbc373592c136bd4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### IRCoT EM: 4.39. Result ID: 6a1945defbc373592c136bce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Naive RAG EM: 4.14. Result ID: 6a1945defbc373592c136bcc. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Naive Generation EM: 3.76. Result ID: 6a1945defbc373592c136bd3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Naive Generation EM: 2.62. Result ID: 6a1945defbc373592c136bcb. [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.