# Multi-Hop Question Answering on MuSiQue (EM, F1aware) Source: [Multi-Hop Question Answering on MuSiQue (EM, F1aware)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:38.993Z Evaluation of model performance on the MuSiQue dataset for Multi-Hop Question Answering, measured using Exact Match (EM) and F1aware 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 Question Answering | | Dataset (including any stated split) | MuSiQue | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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. - [F1aware](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | Search-R1 | 16.1 | Not recorded | 6944dc29423ea42265729cf9 | | Search-R1 | 14.6 | Not recorded | 6944dc29423ea42265729cf9 | | ADASEARCH | 14.4 | Not recorded | 6944dc29423ea42265729cf9 | | ADASEARCH | 13.2 | Not recorded | 6944dc29423ea42265729cf9 | | Awareness Shaping | 13 | Not recorded | 6944dc29423ea42265729cf9 | | Awareness Shaping | 12.5 | Not recorded | 6944dc29423ea42265729cf9 | | IKEA | 11.5 | Not recorded | 6944dc29423ea42265729cf9 | | Naive Shaping | 11.5 | Not recorded | 6944dc29423ea42265729cf9 | | IKEA | 11.2 | Not recorded | 6944dc29423ea42265729cf9 | | Naive Shaping | 9.9 | Not recorded | 6944dc29423ea42265729cf9 | | RL w/o search | 6.7 | Not recorded | 6944dc29423ea42265729cf9 | | RL w/o search | 5.9 | Not recorded | 6944dc29423ea42265729cf9 | | CoT | 4.5 | Not recorded | 6944dc29423ea42265729cf9 | | RAG | 4.4 | Not recorded | 6944dc29423ea42265729cf9 | | RAG | 4.1 | Not recorded | 6944dc29423ea42265729cf9 | | CoT | 3.9 | Not recorded | 6944dc29423ea42265729cf9 | | Direct Answer | 3 | Not recorded | 6944dc29423ea42265729cf9 | | Direct Answer | 1.4 | Not recorded | 6944dc29423ea42265729cf9 | ### Search-R1 EM: 16.1. Result ID: 6996b9bb5698665ec404720d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### Search-R1 EM: 14.6. Result ID: 6996b9bb5698665ec4047216. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### ADASEARCH EM: 14.4. Result ID: 6996b9bb5698665ec4047211. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Paper Method"}. This record does not assert independent reproduction. ### ADASEARCH EM: 13.2. Result ID: 6996b9bb5698665ec404721a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Paper Method"}. This record does not assert independent reproduction. ### Awareness Shaping EM: 13. Result ID: 6996b9bb5698665ec4047218. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Awareness Shaping EM: 12.5. Result ID: 6996b9bb5698665ec404720f. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### IKEA EM: 11.5. Result ID: 6996b9bb5698665ec4047210. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Naive Shaping EM: 11.5. Result ID: 6996b9bb5698665ec4047217. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### IKEA EM: 11.2. Result ID: 6996b9bb5698665ec4047219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Naive Shaping EM: 9.9. Result ID: 6996b9bb5698665ec404720e. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### RL w/o search EM: 6.7. Result ID: 6996b9bb5698665ec4047215. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### RL w/o search EM: 5.9. Result ID: 6996b9bb5698665ec404720c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### CoT EM: 4.5. Result ID: 6996b9bb5698665ec4047213. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### RAG EM: 4.4. Result ID: 6996b9bb5698665ec404720b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### RAG EM: 4.1. Result ID: 6996b9bb5698665ec4047214. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### CoT EM: 3.9. Result ID: 6996b9bb5698665ec404720a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### Direct Answer EM: 3. Result ID: 6996b9bb5698665ec4047212. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### Direct Answer EM: 1.4. Result ID: 6996b9bb5698665ec4047209. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.