# Multi-hop Question Answering on MMhops Bridging (test) Source: [Multi-hop Question Answering on MMhops Bridging (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:49.584Z Evaluation of model performance on the test split of the MMhops Bridging 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) | MMhops Bridging (test) | | Metric | String Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [String Success Rate](): Higher is better; unit: PERCENT. - [Numerical Success Rate](): Higher is better; unit: PERCENT. - [Average Inference Time](): Lower is better; unit: TIME. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | String Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Gemini-2.5-pro | 58.8 | Not recorded | 6940e7e1456146936284fc83 | | Gemini-2.5-flash | 51.08 | Not recorded | 6940e7e1456146936284fc83 | | MMhops-R1 | 44.66 | Not recorded | 6940e7e1456146936284fc83 | | GPT-4o | 41.66 | Not recorded | 6940e7e1456146936284fc83 | | Zero-shot | 37.51 | Not recorded | 6940e7e1456146936284fc83 | | OmniSearch | 31.02 | Not recorded | 6940e7e1456146936284fc83 | | GPT-4o-mini | 29.67 | Not recorded | 6940e7e1456146936284fc83 | | Self-Ask | 27.59 | Not recorded | 6940e7e1456146936284fc83 | | Vanilla mRAG | 26.52 | Not recorded | 6940e7e1456146936284fc83 | | Zero-shot | 24.21 | Not recorded | 6940e7e1456146936284fc83 | | EchoSight | 19.14 | Not recorded | 6940e7e1456146936284fc83 | | Search-r1 | 14.45 | Not recorded | 6940e7e1456146936284fc83 | | Vanilla mRAG | 14.37 | Not recorded | 6940e7e1456146936284fc83 | ### Gemini-2.5-pro String Success Rate: 58.8. Result ID: 699845af5698665ec4a265b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":null,"Retriever":null}. This record does not assert independent reproduction. ### Gemini-2.5-flash String Success Rate: 51.08. Result ID: 699845af5698665ec4a265b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":null,"Retriever":null}. This record does not assert independent reproduction. ### MMhops-R1 String Success Rate: 44.66. Result ID: 699845af5698665ec4a265bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-vl-7B-Instruct","Retriever":"Image, Text"}. This record does not assert independent reproduction. ### GPT-4o String Success Rate: 41.66. Result ID: 699845af5698665ec4a265b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":null,"Retriever":null}. This record does not assert independent reproduction. ### Zero-shot String Success Rate: 37.51. Result ID: 699845af5698665ec4a265b4. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-vl-72B-Instruct","Retriever":null}. This record does not assert independent reproduction. ### OmniSearch String Success Rate: 31.02. Result ID: 699845af5698665ec4a265ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"GPT-4o","Retriever":"Image, Text"}. This record does not assert independent reproduction. ### GPT-4o-mini String Success Rate: 29.67. Result ID: 699845af5698665ec4a265af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":null,"Retriever":null}. This record does not assert independent reproduction. ### Self-Ask String Success Rate: 27.59. Result ID: 699845af5698665ec4a265b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"GPT-4o","Retriever":"Caption, Text"}. This record does not assert independent reproduction. ### Vanilla mRAG String Success Rate: 26.52. Result ID: 699845af5698665ec4a265b8. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-vl-7B-Instruct","Retriever":"Image, Text"}. This record does not assert independent reproduction. ### Zero-shot String Success Rate: 24.21. Result ID: 699845af5698665ec4a265b3. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-vl-7B-Instruct","Retriever":null}. This record does not assert independent reproduction. ### EchoSight String Success Rate: 19.14. Result ID: 699845af5698665ec4a265b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaMA3","Retriever":"Image, Text"}. This record does not assert independent reproduction. ### Search-r1 String Success Rate: 14.45. Result ID: 699845af5698665ec4a265b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7b-Instruct","Retriever":"Caption, Text"}. This record does not assert independent reproduction. ### Vanilla mRAG String Success Rate: 14.37. Result ID: 699845af5698665ec4a265b7. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-vl-7B-Instruct","Retriever":"Text"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.