# Multi-hop Question Answering on 2Wiki (MBE, Recall, Searches) Source: [Multi-hop Question Answering on 2Wiki (MBE, Recall, Searches)]() Collection index: [llms.txt]() Data updated: 2026-03-04T08:04:01.777Z Evaluation of model performance on the 2Wiki dataset for multi-hop question answering, specifically measured using MBE, Recall, and Searches 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) | 2Wiki | | Metric | MBE | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [MBE](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Searches](): Lower is better; unit: SCALAR. ## Recorded results | Method | MBE | Result date | Report paper | | --- | --- | --- | --- | | CoRAG | 59 | Not recorded | 68fa7a4d1e209131cea82501 | | R1-Searcher | 52 | Not recorded | 68fa7a4d1e209131cea82501 | | FRUGALRAG-7B + CoRAG | 51.2 | Not recorded | 68fa7a4d1e209131cea82501 | | FRUGALRAG-7B + Qwen2.5-32B-Inst | 50.9 | Not recorded | 68fa7a4d1e209131cea82501 | | FRUGALRAG-7B + Qwen2.5-7B-Inst | 50.4 | Not recorded | 68fa7a4d1e209131cea82501 | | SimpleDeepSearcher | 49.3 | Not recorded | 68fa7a4d1e209131cea82501 | | O2 Searcher | 45.7 | Not recorded | 68fa7a4d1e209131cea82501 | | Ret-Robust | 45.17 | Not recorded | 68fa7a4d1e209131cea82501 | | Search-R1 | 36.2 | Not recorded | 68fa7a4d1e209131cea82501 | | ReAct + DsPy | 35.65 | Not recorded | 68fa7a4d1e209131cea82501 | | ITER-RETGEN | 32.1 | Not recorded | 68fa7a4d1e209131cea82501 | | Self RAG 13B | 31.5 | Not recorded | 68fa7a4d1e209131cea82501 | | IRCOT | 30.53 | Not recorded | 68fa7a4d1e209131cea82501 | | Self RAG 7B | 30.1 | Not recorded | 68fa7a4d1e209131cea82501 | | Zero-Shot CoT | 29.8 | Not recorded | 68fa7a4d1e209131cea82501 | | Zero-Shot RAG | 28.8 | Not recorded | 68fa7a4d1e209131cea82501 | | Zero-Shot | 28.4 | Not recorded | 68fa7a4d1e209131cea82501 | ### CoRAG MBE: 59. Result ID: 69a7e58d6dbb7075b94c909c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"\>100k"}. This record does not assert independent reproduction. ### R1-Searcher MBE: 52. Result ID: 69a7e58d6dbb7075b94c909a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"8k"}. This record does not assert independent reproduction. ### FRUGALRAG-7B + CoRAG MBE: 51.2. Result ID: 69a7e58d6dbb7075b94c909f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"1000"}. This record does not assert independent reproduction. ### FRUGALRAG-7B + Qwen2.5-32B-Inst MBE: 50.9. Result ID: 69a7e58d6dbb7075b94c909e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"1000"}. This record does not assert independent reproduction. ### FRUGALRAG-7B + Qwen2.5-7B-Inst MBE: 50.4. Result ID: 69a7e58d6dbb7075b94c909d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"1000"}. This record does not assert independent reproduction. ### SimpleDeepSearcher MBE: 49.3. Result ID: 69a7e58d6dbb7075b94c9099. [Reporting paper]() Recorded evaluation configuration: {"#Train":"871"}. This record does not assert independent reproduction. ### O2 Searcher MBE: 45.7. Result ID: 69a7e58d6dbb7075b94c9098. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"1440"}. This record does not assert independent reproduction. ### Ret-Robust MBE: 45.17. Result ID: 69a7e58d6dbb7075b94c9095. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Train":"1000"}. This record does not assert independent reproduction. ### Search-R1 MBE: 36.2. Result ID: 69a7e58d6dbb7075b94c909b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"\>100k"}. This record does not assert independent reproduction. ### ReAct + DsPy MBE: 35.65. Result ID: 69a7e58d6dbb7075b94c9092. [Reporting paper]() Recorded evaluation configuration: {"#Train":"100"}. This record does not assert independent reproduction. ### ITER-RETGEN MBE: 32.1. Result ID: 69a7e58d6dbb7075b94c9094. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Train":"36k"}. This record does not assert independent reproduction. ### Self RAG 13B MBE: 31.5. Result ID: 69a7e58d6dbb7075b94c9097. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Train":"150k"}. This record does not assert independent reproduction. ### IRCOT MBE: 30.53. Result ID: 69a7e58d6dbb7075b94c9093. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Train":"–"}. This record does not assert independent reproduction. ### Self RAG 7B MBE: 30.1. Result ID: 69a7e58d6dbb7075b94c9096. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Train":"150k"}. This record does not assert independent reproduction. ### Zero-Shot CoT MBE: 29.8. Result ID: 69a7e58d6dbb7075b94c9090. [Reporting paper]() Recorded evaluation configuration: {"#Train":"–"}. This record does not assert independent reproduction. ### Zero-Shot RAG MBE: 28.8. Result ID: 69a7e58d6dbb7075b94c9091. [Reporting paper]() Recorded evaluation configuration: {"#Train":"–"}. This record does not assert independent reproduction. ### Zero-Shot MBE: 28.4. Result ID: 69a7e58d6dbb7075b94c908f. [Reporting paper]() Recorded evaluation configuration: {"#Train":"–"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.