# Search-based Visual Question Answering on WebEyes 1.0 (test) Source: [Search-based Visual Question Answering on WebEyes 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T11:34:51.357Z Evaluation of model performance on the test split of the WebEyes 1.0 dataset for Search-based Visual Question Answering, reporting category-specific accuracies (e.g., Vehicles, Anime) and 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 | Search-based Visual Question Answering | | Dataset (including any stated split) | WebEyes 1.0 (test) | | Metric | Accuracy (Vehicles) | | 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 (Vehicles)](): Higher is better; unit: PERCENT. - [Accuracy (Pop-IP)](): Higher is better; unit: PERCENT. - [Accuracy (Anime)](): Higher is better; unit: PERCENT. - [Accuracy (ICON)](): Higher is better; unit: PERCENT. - [Accuracy (Celebrities)](): Higher is better; unit: PERCENT. - [Accuracy (PRODUCT)](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Vehicles) | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3.1-Pro | 83.33 | Not recorded | 6a0405eadbc836b87d8279c1 | | Doubao-Seed-1.8 | 69.44 | Not recorded | 6a0405eadbc836b87d8279c1 | | Doubao-Seed-2.0-Pro | 69.44 | Not recorded | 6a0405eadbc836b87d8279c1 | | Doubao-Seed-1.6 | 63.89 | Not recorded | 6a0405eadbc836b87d8279c1 | | GPT-4.1 | 58.33 | Not recorded | 6a0405eadbc836b87d8279c1 | | GPT-4o | 58.33 | Not recorded | 6a0405eadbc836b87d8279c1 | | Gemini-3.1-Flash-Lite | 55.56 | Not recorded | 6a0405eadbc836b87d8279c1 | | Qwen3-VL-8B | 47.22 | Not recorded | 6a0405eadbc836b87d8279c1 | | GPT-5.4 | 44.44 | Not recorded | 6a0405eadbc836b87d8279c1 | | SophiaVL-R1 | 38.89 | Not recorded | 6a0405eadbc836b87d8279c1 | | Pixel-Searcher | 38.89 | Not recorded | 6a0405eadbc836b87d8279c1 | | OneThinker-8B | 36.11 | Not recorded | 6a0405eadbc836b87d8279c1 | | VL-Rethinker | 33.33 | Not recorded | 6a0405eadbc836b87d8279c1 | | UniVG-R1 | 30.56 | Not recorded | 6a0405eadbc836b87d8279c1 | | InternVL-3.5-8B | 25 | Not recorded | 6a0405eadbc836b87d8279c1 | | Vision-R1 | 13.89 | Not recorded | 6a0405eadbc836b87d8279c1 | ### Gemini-3.1-Pro Accuracy (Vehicles): 83.33. Result ID: 6a0460b047f34ce924eb4310. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### Doubao-Seed-1.8 Accuracy (Vehicles): 69.44. Result ID: 6a0460b047f34ce924eb430a. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### Doubao-Seed-2.0-Pro Accuracy (Vehicles): 69.44. Result ID: 6a0460b047f34ce924eb430b. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### Doubao-Seed-1.6 Accuracy (Vehicles): 63.89. Result ID: 6a0460b047f34ce924eb4309. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### GPT-4.1 Accuracy (Vehicles): 58.33. Result ID: 6a0460b047f34ce924eb430c. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### GPT-4o Accuracy (Vehicles): 58.33. Result ID: 6a0460b047f34ce924eb430e. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### Gemini-3.1-Flash-Lite Accuracy (Vehicles): 55.56. Result ID: 6a0460b047f34ce924eb430f. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy (Vehicles): 47.22. Result ID: 6a0460b047f34ce924eb4317. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source General Models"}. This record does not assert independent reproduction. ### GPT-5.4 Accuracy (Vehicles): 44.44. Result ID: 6a0460b047f34ce924eb430d. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source Models"}. This record does not assert independent reproduction. ### SophiaVL-R1 Accuracy (Vehicles): 38.89. Result ID: 6a0460b047f34ce924eb4312. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source QA Models"}. This record does not assert independent reproduction. ### Pixel-Searcher Accuracy (Vehicles): 38.89. Result ID: 6a0460b047f34ce924eb4318. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Proposed Method"}. This record does not assert independent reproduction. ### OneThinker-8B Accuracy (Vehicles): 36.11. Result ID: 6a0460b047f34ce924eb4315. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Open-Source General Models"}. This record does not assert independent reproduction. ### VL-Rethinker Accuracy (Vehicles): 33.33. Result ID: 6a0460b047f34ce924eb4313. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source QA Models"}. This record does not assert independent reproduction. ### UniVG-R1 Accuracy (Vehicles): 30.56. Result ID: 6a0460b047f34ce924eb4311. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source QA Models"}. This record does not assert independent reproduction. ### InternVL-3.5-8B Accuracy (Vehicles): 25. Result ID: 6a0460b047f34ce924eb4316. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source General Models"}. This record does not assert independent reproduction. ### Vision-R1 Accuracy (Vehicles): 13.89. Result ID: 6a0460b047f34ce924eb4314. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source QA Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.