# Multimodal Long-document Understanding on MMLongBench-Doc 1.0 (test) Source: [Multimodal Long-document Understanding on MMLongBench-Doc 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-09T07:03:53.794Z Evaluation of multimodal model performance on the MMLongBench-Doc dataset version 1.0 test split, assessing understanding across various document categories like Reports, Tutorials, and Financial documents. 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 Long-document Understanding | | Dataset (including any stated split) | MMLongBench-Doc 1.0 (test) | | Metric | Reports Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Reports Score](): Higher is better; unit: PERCENT. - [Reports Accuracy](): Higher is better; unit: PERCENT. - [Tutorials Accuracy](): Higher is better; unit: PERCENT. - [Tutorials Score](): Higher is better; unit: PERCENT. - [Academic Accuracy](): Higher is better; unit: PERCENT. - [Academic Score](): Higher is better; unit: PERCENT. - [Guidebooks Accuracy](): Higher is better; unit: PERCENT. - [Guidebooks Score](): Higher is better; unit: PERCENT. - [Brochures Accuracy](): Higher is better; unit: PERCENT. - [Brochures Score](): Higher is better; unit: PERCENT. - [Industry Accuracy](): Higher is better; unit: PERCENT. - [Industry Score](): Higher is better; unit: PERCENT. - [Financial Accuracy](): Higher is better; unit: PERCENT. - [Financial Score](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Reports Score | Result date | Report paper | | --- | --- | --- | --- | | BayesRAG | 46.7 | Not recorded | 6965d19b6343fa78c83236ae | | RAGAnything | 45.3 | Not recorded | 6965d19b6343fa78c83236ae | | AutothinkRAG | 44.86 | Not recorded | 69ae53f52d603e6de3e429f6 | | Nothink | 43.15 | Not recorded | 69ae53f52d603e6de3e429f6 | | 8B | 42.8 | Not recorded | 69ae53f52d603e6de3e429f6 | | VLM only | 41.43 | Not recorded | 69ae53f52d603e6de3e429f6 | | Raganything | 41.09 | Not recorded | 69ae53f52d603e6de3e429f6 | | baseline | 40.41 | Not recorded | 69ae53f52d603e6de3e429f6 | | RAGFlow | 38.9 | Not recorded | 6965d19b6343fa78c83236ae | | GPT-4o-mini | 36.7 | Not recorded | 6965d19b6343fa78c83236ae | | ViDoRAG | 36.1 | Not recorded | 6965d19b6343fa78c83236ae | | VisRAG | 30 | Not recorded | 6965d19b6343fa78c83236ae | ### BayesRAG Reports Score: 46.7. Result ID: 69968e275698665ec4d6fa34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RAGAnything Reports Score: 45.3. Result ID: 69968e275698665ec4d6fa33. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AutothinkRAG Reports Score: 44.86. Result ID: 69ae70d06dbb7075b95606a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Nothink Reports Score: 43.15. Result ID: 69ae70d06dbb7075b95606a8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### 8B Reports Score: 42.8. Result ID: 69ae70d06dbb7075b95606ab. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VLM only Reports Score: 41.43. Result ID: 69ae70d06dbb7075b95606a9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Raganything Reports Score: 41.09. Result ID: 69ae70d06dbb7075b95606ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### baseline Reports Score: 40.41. Result ID: 69ae70d06dbb7075b95606aa. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RAGFlow Reports Score: 38.9. Result ID: 69968e275698665ec4d6fa32. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o-mini Reports Score: 36.7. Result ID: 69968e275698665ec4d6fa2f. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ViDoRAG Reports Score: 36.1. Result ID: 69968e275698665ec4d6fa31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VisRAG Reports Score: 30. Result ID: 69968e275698665ec4d6fa30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.