# Multi-hop Question Answering on Bamboogle (SR) Source: [Multi-hop Question Answering on Bamboogle (SR)]() Collection index: [llms.txt]() Data updated: 2026-05-18T06:38:29.267Z Evaluation of model performance on the Bamboogle 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) | Bamboogle | | 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 | 72 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Gemini-2.5-flash | 59.5 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-30B-A3B | 44 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GSPO | 42 | Not recorded | 6a0a9d04dbc836b87d82b322 | | MATPO | 41 | Not recorded | 6a0a9d04dbc836b87d82b322 | | MATPO | 40 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ICRL | 40 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Critique-GRPO | 38.5 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ICRL | 38 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GRPO | 38 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ScalingInter | 38 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Critique-GRPO | 38 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GSPO | 34 | Not recorded | 6a0a9d04dbc836b87d82b322 | | ScalingInter | 32 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-8B | 30 | Not recorded | 6a0a9d04dbc836b87d82b322 | | GRPO | 30 | Not recorded | 6a0a9d04dbc836b87d82b322 | | Qwen3-4B | 26 | Not recorded | 6a0a9d04dbc836b87d82b322 | ### Gemini-3-Flash SR: 72. Result ID: 6a0ab3d347f34ce924f03294. [Reporting paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### Gemini-2.5-flash SR: 59.5. Result ID: 6a0ab3d347f34ce924f03293. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B SR: 44. Result ID: 6a0ab3d347f34ce924f03292. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### GSPO SR: 42. Result ID: 6a0ab3d347f34ce924f0329c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### MATPO SR: 41. Result ID: 6a0ab3d347f34ce924f0329e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### MATPO SR: 40. Result ID: 6a0ab3d347f34ce924f03298. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### ICRL SR: 40. Result ID: 6a0ab3d347f34ce924f032a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Critique-GRPO SR: 38.5. Result ID: 6a0ab3d347f34ce924f03299. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### ICRL SR: 38. Result ID: 6a0ab3d347f34ce924f0329a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GRPO SR: 38. Result ID: 6a0ab3d347f34ce924f0329b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ScalingInter SR: 38. Result ID: 6a0ab3d347f34ce924f0329d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Critique-GRPO SR: 38. Result ID: 6a0ab3d347f34ce924f0329f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GSPO SR: 34. Result ID: 6a0ab3d347f34ce924f03296. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### ScalingInter SR: 32. Result ID: 6a0ab3d347f34ce924f03297. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Qwen3-8B SR: 30. Result ID: 6a0ab3d347f34ce924f03291. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Prompting"}. This record does not assert independent reproduction. ### GRPO SR: 30. Result ID: 6a0ab3d347f34ce924f03295. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Qwen3-4B SR: 26. Result ID: 6a0ab3d347f34ce924f03290. [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.