# Real-world Perception on RealWorldQA Source: [Real-world Perception on RealWorldQA]() Collection index: [llms.txt]() Data updated: 2026-05-19T07:41:21.357Z Evaluation of model performance on the RealWorldQA dataset for the Real-world Perception task, measured by 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 | Real-world Perception | | Dataset (including any stated split) | RealWorldQA | | Metric | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL-2B | 65.1 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 63.68 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 63.01 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 62.88 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 62.75 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 62.35 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 62.35 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 62.35 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 61.83 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 61.57 | Not recorded | 6a0bee84dbc836b87d82c339 | | F3A | 61.57 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 61.05 | Not recorded | 6a0bee84dbc836b87d82c339 | | DivPrune | 59.87 | Not recorded | 6a0bee84dbc836b87d82c339 | | CDPruner | 59.35 | Not recorded | 6a0bee84dbc836b87d82c339 | | VisionZip | 58.56 | Not recorded | 6a0bee84dbc836b87d82c339 | | FastV | 56.08 | Not recorded | 6a0bee84dbc836b87d82c339 | ### Qwen3-VL-2B Accuracy: 65.1. Result ID: 6a0c13f3fbc373592c01d42d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"100%"}. This record does not assert independent reproduction. ### F3A Accuracy: 63.68. Result ID: 6a0c13f3fbc373592c01d432. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### FastV Accuracy: 63.01. Result ID: 6a0c13f3fbc373592c01d42f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### CDPruner Accuracy: 62.88. Result ID: 6a0c13f3fbc373592c01d42e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### F3A Accuracy: 62.75. Result ID: 6a0c13f3fbc373592c01d437. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### DivPrune Accuracy: 62.35. Result ID: 6a0c13f3fbc373592c01d430. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### VisionZip Accuracy: 62.35. Result ID: 6a0c13f3fbc373592c01d431. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"60%"}. This record does not assert independent reproduction. ### CDPruner Accuracy: 62.35. Result ID: 6a0c13f3fbc373592c01d433. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### VisionZip Accuracy: 61.83. Result ID: 6a0c13f3fbc373592c01d436. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### DivPrune Accuracy: 61.57. Result ID: 6a0c13f3fbc373592c01d435. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### F3A Accuracy: 61.57. Result ID: 6a0c13f3fbc373592c01d43c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### FastV Accuracy: 61.05. Result ID: 6a0c13f3fbc373592c01d434. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"40%"}. This record does not assert independent reproduction. ### DivPrune Accuracy: 59.87. Result ID: 6a0c13f3fbc373592c01d43a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### CDPruner Accuracy: 59.35. Result ID: 6a0c13f3fbc373592c01d438. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### VisionZip Accuracy: 58.56. Result ID: 6a0c13f3fbc373592c01d43b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ratio":"20%"}. This record does not assert independent reproduction. ### FastV Accuracy: 56.08. Result ID: 6a0c13f3fbc373592c01d439. [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.