# Multi-hop Question Answering on 2WikiMultiHopQA (SR) Source: [Multi-hop Question Answering on 2WikiMultiHopQA (SR)]() Collection index: [llms.txt]() Data updated: 2026-05-18T06:38:29.229Z Evaluation of model performance on the 2WikiMultiHopQA dataset for multi-hop question answering, specifically reporting the Success Rate (SR) metric. 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) | 2WikiMultiHopQA | | Metric | SR | | 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 - [SR](): Higher is better; unit: PERCENT. ## Recorded results | Method | SR | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3-Flash | 78 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Gemini-2.5-flash | 66 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-30B-A3B | 58 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ICRL | 50 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Critique-GRPO | 47.5 | Not recorded | 6a0a9d04dbc836b87d82b322 | | MATPO | 46 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ICRL | 45 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GSPO | 44.5 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Critique-GRPO | 43 | Not recorded | 6a0a9d04dbc836b87d82b322 | | MATPO | 42 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GRPO | 42 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ScalingInter | 40 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ScalingInter | 38 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GRPO | 36 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GSPO | 36 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-4B | 32 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-8B | 32 | Not recorded | 6a0a9d04dbc836b87d82b322 | ### Gemini-3-Flash SR: 78. Result ID: 6a0ab3d347f34ce924f03283. [Reporting paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### Gemini-2.5-flash SR: 66. Result ID: 6a0ab3d347f34ce924f03282. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B SR: 58. Result ID: 6a0ab3d347f34ce924f03281. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### ICRL SR: 50. Result ID: 6a0ab3d347f34ce924f0328f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Critique-GRPO SR: 47.5. Result ID: 6a0ab3d347f34ce924f0328e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### MATPO SR: 46. Result ID: 6a0ab3d347f34ce924f0328d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ICRL SR: 45. Result ID: 6a0ab3d347f34ce924f03289. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GSPO SR: 44.5. Result ID: 6a0ab3d347f34ce924f0328b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Critique-GRPO SR: 43. Result ID: 6a0ab3d347f34ce924f03288. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### MATPO SR: 42. Result ID: 6a0ab3d347f34ce924f03287. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GRPO SR: 42. Result ID: 6a0ab3d347f34ce924f0328a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ScalingInter SR: 40. Result ID: 6a0ab3d347f34ce924f0328c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ScalingInter SR: 38. Result ID: 6a0ab3d347f34ce924f03286. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GRPO SR: 36. Result ID: 6a0ab3d347f34ce924f03284. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GSPO SR: 36. Result ID: 6a0ab3d347f34ce924f03285. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Qwen3-4B SR: 32. Result ID: 6a0ab3d347f34ce924f0327f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### Qwen3-8B SR: 32. Result ID: 6a0ab3d347f34ce924f03280. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.