# Multi-hop Question Answering on MARCH Source: [Multi-hop Question Answering on MARCH]() Collection index: [llms.txt]() Data updated: 2026-04-10T07:08:40.064Z Evaluation of model performance on the MARCH dataset for multi-hop question answering. 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) | MARCH | | Metric | Exact Match (EM) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Exact Match (EM)](): Higher is better; unit: SCALAR. - [F1 Score (Disambiguation)](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. - [LLM Judge Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Exact Match (EM) | Result date | Report paper | | --- | --- | --- | --- | | Human | 73 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION | 38.73 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION | 31.47 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION | 29.12 | Not recorded | 68fa7ba61e209131cea899f5 | | DIVA | 28.82 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT w/ RAG | 25.63 | Not recorded | 68fa7ba61e209131cea899f5 | | NaiveRAG | 25.1 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification | 25.1 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification & detection | 24.51 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification | 24.12 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification & detection | 23.82 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification | 23.63 | Not recorded | 68fa7ba61e209131cea899f5 | | ReAct | 23.17 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT w/ RAG | 23.15 | Not recorded | 68fa7ba61e209131cea899f5 | | CLARION w/o clarification & detection | 22.94 | Not recorded | 68fa7ba61e209131cea899f5 | | NaiveRAG | 22.16 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT | 21.51 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT w/ RAG | 21.33 | Not recorded | 68fa7ba61e209131cea899f5 | | ReAct | 21.32 | Not recorded | 68fa7ba61e209131cea899f5 | | No Retrieval | 20.98 | Not recorded | 68fa7ba61e209131cea899f5 | | ReAct | 20.98 | Not recorded | 68fa7ba61e209131cea899f5 | | NaiveRAG | 20.2 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT | 19.8 | Not recorded | 68fa7ba61e209131cea899f5 | | DIVA | 18.82 | Not recorded | 68fa7ba61e209131cea899f5 | | DIVA | 18.82 | Not recorded | 68fa7ba61e209131cea899f5 | | No Retrieval | 17.75 | Not recorded | 68fa7ba61e209131cea899f5 | | CoT | 16.32 | Not recorded | 68fa7ba61e209131cea899f5 | | No Retrieval | 15.59 | Not recorded | 68fa7ba61e209131cea899f5 | ### Human Exact Match (EM): 73. Result ID: 69d8a13147f34ce924c1048c. [Reporting paper]() Recorded evaluation configuration: {"Model":"N/A"}. This record does not assert independent reproduction. ### CLARION Exact Match (EM): 38.73. Result ID: 69d8a13147f34ce924c10477. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### CLARION Exact Match (EM): 31.47. Result ID: 69d8a13147f34ce924c10489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### CLARION Exact Match (EM): 29.12. Result ID: 69d8a13147f34ce924c10480. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### DIVA Exact Match (EM): 28.82. Result ID: 69d8a13147f34ce924c10475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### CoT w/ RAG Exact Match (EM): 25.63. Result ID: 69d8a13147f34ce924c10474. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### NaiveRAG Exact Match (EM): 25.1. Result ID: 69d8a13147f34ce924c10473. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### CLARION w/o clarification Exact Match (EM): 25.1. Result ID: 69d8a13147f34ce924c10478. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### CLARION w/o clarification & detection Exact Match (EM): 24.51. Result ID: 69d8a13147f34ce924c1048b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### CLARION w/o clarification Exact Match (EM): 24.12. Result ID: 69d8a13147f34ce924c10481. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### CLARION w/o clarification & detection Exact Match (EM): 23.82. Result ID: 69d8a13147f34ce924c10482. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### CLARION w/o clarification Exact Match (EM): 23.63. Result ID: 69d8a13147f34ce924c1048a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### ReAct Exact Match (EM): 23.17. Result ID: 69d8a13147f34ce924c10488. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### CoT w/ RAG Exact Match (EM): 23.15. Result ID: 69d8a13147f34ce924c1047d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### CLARION w/o clarification & detection Exact Match (EM): 22.94. Result ID: 69d8a13147f34ce924c10479. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### NaiveRAG Exact Match (EM): 22.16. Result ID: 69d8a13147f34ce924c1047c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### CoT Exact Match (EM): 21.51. Result ID: 69d8a13147f34ce924c10472. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### CoT w/ RAG Exact Match (EM): 21.33. Result ID: 69d8a13147f34ce924c10486. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### ReAct Exact Match (EM): 21.32. Result ID: 69d8a13147f34ce924c1047f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### No Retrieval Exact Match (EM): 20.98. Result ID: 69d8a13147f34ce924c10471. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### ReAct Exact Match (EM): 20.98. Result ID: 69d8a13147f34ce924c10476. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-235b"}. This record does not assert independent reproduction. ### NaiveRAG Exact Match (EM): 20.2. Result ID: 69d8a13147f34ce924c10485. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### CoT Exact Match (EM): 19.8. Result ID: 69d8a13147f34ce924c10484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### DIVA Exact Match (EM): 18.82. Result ID: 69d8a13147f34ce924c1047e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### DIVA Exact Match (EM): 18.82. Result ID: 69d8a13147f34ce924c10487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### No Retrieval Exact Match (EM): 17.75. Result ID: 69d8a13147f34ce924c10483. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek-v3.1"}. This record does not assert independent reproduction. ### CoT Exact Match (EM): 16.32. Result ID: 69d8a13147f34ce924c1047b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. ### No Retrieval Exact Match (EM): 15.59. Result ID: 69d8a13147f34ce924c1047a. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemini-2.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.