# Aggregate Multimodal Performance on Multimodal Evaluation Summary Source: [Aggregate Multimodal Performance on Multimodal Evaluation Summary]() Collection index: [llms.txt]() Data updated: 2026-05-19T07:41:21.473Z An evaluation summarizing the aggregated performance across multimodal tasks using the 'Multimodal Evaluation Summary' dataset, reporting key metrics such as Average Accuracy and Relative Performance Ratio. 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 | Aggregate Multimodal Performance | | Dataset (including any stated split) | Multimodal Evaluation Summary | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Relative Performance Ratio](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL-2B | 74.89 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 72.98 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 72.79 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 72.69 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 72.65 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 72.38 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 72.31 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 71.78 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 71.69 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 71.67 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 70.94 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 70.66 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 69.55 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 69.17 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 67.85 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 66.22 | Not recorded | 6a0bee84dbc836b87d82c339 | ### Qwen3-VL-2B Average Accuracy: 74.89. Result ID: 6a0c13f3fbc373592c01d4ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"100%"}. This record does not assert independent reproduction. ### F3A Average Accuracy: 72.98. Result ID: 6a0c13f3fbc373592c01d4b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### CDPruner Average Accuracy: 72.79. Result ID: 6a0c13f3fbc373592c01d4ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### VisionZip Average Accuracy: 72.69. Result ID: 6a0c13f3fbc373592c01d4b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### DivPrune Average Accuracy: 72.65. Result ID: 6a0c13f3fbc373592c01d4b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### F3A Average Accuracy: 72.38. Result ID: 6a0c13f3fbc373592c01d4b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### FastV Average Accuracy: 72.31. Result ID: 6a0c13f3fbc373592c01d4af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### CDPruner Average Accuracy: 71.78. Result ID: 6a0c13f3fbc373592c01d4b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### VisionZip Average Accuracy: 71.69. Result ID: 6a0c13f3fbc373592c01d4b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### DivPrune Average Accuracy: 71.67. Result ID: 6a0c13f3fbc373592c01d4b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### FastV Average Accuracy: 70.94. Result ID: 6a0c13f3fbc373592c01d4b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### F3A Average Accuracy: 70.66. Result ID: 6a0c13f3fbc373592c01d4bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### CDPruner Average Accuracy: 69.55. Result ID: 6a0c13f3fbc373592c01d4b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### DivPrune Average Accuracy: 69.17. Result ID: 6a0c13f3fbc373592c01d4ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### VisionZip Average Accuracy: 67.85. Result ID: 6a0c13f3fbc373592c01d4bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### FastV Average Accuracy: 66.22. Result ID: 6a0c13f3fbc373592c01d4b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.