# Multimodal Question Answering on M2RAG Source: [Multimodal Question Answering on M2RAG]() Collection index: [llms.txt]() Data updated: 2026-04-28T10:31:28.999Z Evaluation of model performance on the M2RAG dataset for Multimodal Question Answering tasks, measured using metrics such as B-scores, ROUGE scores, and CIDEr. 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 | Multimodal Question Answering | | Dataset (including any stated split) | M2RAG | | Metric | B-1 Score | | Unit | PERCENT | | 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 - [B-1 Score](): Higher is better; unit: PERCENT. - [B-2 Score](): Higher is better; unit: PERCENT. - [B-3 Score](): Higher is better; unit: PERCENT. - [B-4 Score](): Higher is better; unit: PERCENT. - [ROUGE-1 Score](): Higher is better; unit: PERCENT. - [ROUGE-2 Score](): Higher is better; unit: PERCENT. - [ROUGE-L Score](): Higher is better; unit: PERCENT. - [CIDEr Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | B-1 Score | Result date | Report paper | | --- | --- | --- | --- | | Ours-top3 | 42.95 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top1 | 41.84 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top3 | 40.67 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top3 | 40.46 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top1 | 39.16 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top1 | 38.12 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top3 | 37.89 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top1 | 37.28 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top3 | 36.19 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top1 | 35.94 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top1 | 35.73 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top3 | 35.73 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top0 | 34.85 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top3 | 34.26 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top0 | 33.88 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top1 | 33.69 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top3 | 33.37 | Not recorded | 69f03f8155a3c32af89fa5e5 | | Ours-top1 | 32.5 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top1 | 30.76 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top3 | 30.67 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top3 | 30.57 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top1 | 30.04 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top3 | 29.89 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top3 | 29.57 | Not recorded | 69f03f8155a3c32af89fa5e5 | | jinarerank-top1 | 28.93 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top1 | 27.14 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top0 | 25.41 | Not recorded | 69f03f8155a3c32af89fa5e5 | | top0 | 25.34 | Not recorded | 69f03f8155a3c32af89fa5e5 | ### Ours-top3 B-1 Score: 42.95. Result ID: 69f08c6b47f34ce924d733ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### Ours-top1 B-1 Score: 41.84. Result ID: 69f08c6b47f34ce924d733aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### top3 B-1 Score: 40.67. Result ID: 69f08c6b47f34ce924d733ab. [Reporting paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### jinarerank-top3 B-1 Score: 40.46. Result ID: 69f08c6b47f34ce924d733ac. [Reporting paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### jinarerank-top1 B-1 Score: 39.16. Result ID: 69f08c6b47f34ce924d733a9. [Reporting paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### top1 B-1 Score: 38.12. Result ID: 69f08c6b47f34ce924d733a8. [Reporting paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### Ours-top3 B-1 Score: 37.89. Result ID: 69f08c6b47f34ce924d733b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### Ours-top1 B-1 Score: 37.28. Result ID: 69f08c6b47f34ce924d733b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### jinarerank-top3 B-1 Score: 36.19. Result ID: 69f08c6b47f34ce924d733b3. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### jinarerank-top1 B-1 Score: 35.94. Result ID: 69f08c6b47f34ce924d733b0. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### top1 B-1 Score: 35.73. Result ID: 69f08c6b47f34ce924d733af. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### top3 B-1 Score: 35.73. Result ID: 69f08c6b47f34ce924d733b2. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### top0 B-1 Score: 34.85. Result ID: 69f08c6b47f34ce924d733ae. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### Ours-top3 B-1 Score: 34.26. Result ID: 69f08c6b47f34ce924d733bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### top0 B-1 Score: 33.88. Result ID: 69f08c6b47f34ce924d733a7. [Reporting paper]() Recorded evaluation configuration: {"Model":"MM-RAIT (Qwen2.5-VL)"}. This record does not assert independent reproduction. ### Ours-top1 B-1 Score: 33.69. Result ID: 69f08c6b47f34ce924d733b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### Ours-top3 B-1 Score: 33.37. Result ID: 69f08c6b47f34ce924d733c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### Ours-top1 B-1 Score: 32.5. Result ID: 69f08c6b47f34ce924d733bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### jinarerank-top1 B-1 Score: 30.76. Result ID: 69f08c6b47f34ce924d733be. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### top3 B-1 Score: 30.67. Result ID: 69f08c6b47f34ce924d733c0. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### jinarerank-top3 B-1 Score: 30.57. Result ID: 69f08c6b47f34ce924d733ba. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### top1 B-1 Score: 30.04. Result ID: 69f08c6b47f34ce924d733bd. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### jinarerank-top3 B-1 Score: 29.89. Result ID: 69f08c6b47f34ce924d733c1. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### top3 B-1 Score: 29.57. Result ID: 69f08c6b47f34ce924d733b9. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### jinarerank-top1 B-1 Score: 28.93. Result ID: 69f08c6b47f34ce924d733b7. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### top1 B-1 Score: 27.14. Result ID: 69f08c6b47f34ce924d733b6. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. ### top0 B-1 Score: 25.41. Result ID: 69f08c6b47f34ce924d733bc. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-VL"}. This record does not assert independent reproduction. ### top0 B-1 Score: 25.34. Result ID: 69f08c6b47f34ce924d733b5. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL-3.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.