# Visual Document Question Answering on LongDocURL (Filtered) Source: [Visual Document Question Answering on LongDocURL (Filtered)]() Collection index: [llms.txt]() Data updated: 2026-03-09T08:54:31.597Z Evaluation of Visual Document Question Answering performance on the filtered subset of the LongDocURL dataset, reporting overall accuracy. 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 | Visual Document Question Answering | | Dataset (including any stated split) | LongDocURL (Filtered) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Oracle | 67.79 | Not recorded | 68fa7ba71e209131cea89ab7 | | Oracle | 64.81 | Not recorded | 68fa7ba71e209131cea89ab7 | | CMRAG | 48.18 | Not recorded | 68fa7ba71e209131cea89ab7 | | SigLIP | 47.66 | Not recorded | 68fa7ba71e209131cea89ab7 | | CLIP-L/14-336 | 44.42 | Not recorded | 68fa7ba71e209131cea89ab7 | ### Oracle Accuracy: 67.79. Result ID: 69ae8ab06dbb7075b956cee4. [Reporting paper]() Recorded evaluation configuration: {"Top-k retrieval":"3","Input modality":"I + T","Judge model":"Qwen2.5-7B-Instruct","Backbone Vision Language Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### Oracle Accuracy: 64.81. Result ID: 69ae8ab06dbb7075b956cee3. [Reporting paper]() Recorded evaluation configuration: {"Top-k retrieval":"3","Input modality":"I","Judge model":"Qwen2.5-7B-Instruct","Backbone Vision Language Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### CMRAG Accuracy: 48.18. Result ID: 69ae8ab06dbb7075b956cee2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Top-k retrieval":"3","Judge model":"Qwen2.5-7B-Instruct","Backbone Vision Language Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### SigLIP Accuracy: 47.66. Result ID: 69ae8ab06dbb7075b956cee1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Top-k retrieval":"3","Judge model":"Qwen2.5-7B-Instruct","Backbone Vision Language Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### CLIP-L/14-336 Accuracy: 44.42. Result ID: 69ae8ab06dbb7075b956cee0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Top-k retrieval":"3","Judge model":"Qwen2.5-7B-Instruct","Backbone Vision Language Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.