# VLM-based Q/A Quiz on ArcBench VLM-based Q/A Quiz Closed Source: [VLM-based Q/A Quiz on ArcBench VLM-based Q/A Quiz Closed]() Collection index: [llms.txt]() Data updated: 2026-04-15T07:42:16.412Z Evaluation of VLM performance on the ArcBench VLM-based Q/A Quiz Closed dataset, reporting scores across Story, Visuals, Hard, and Depth dimensions. 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 | VLM-based Q/A Quiz | | Dataset (including any stated split) | ArcBench VLM-based Q/A Quiz Closed | | Metric | Story Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Story Accuracy](): Higher is better; unit: PERCENT. - [Visuals Accuracy](): Higher is better; unit: PERCENT. - [Hard Accuracy](): Higher is better; unit: PERCENT. - [Depth Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Story Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SlideGen | 97.6 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 96 | Not recorded | 69df1b987d0172140ec7b92e | | HTML | 95.6 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 93.12 | Not recorded | 69df1b987d0172140ec7b92e | | SlideGen | 90.42 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 87 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 86.14 | Not recorded | 69df1b987d0172140ec7b92e | | HTML | 85.67 | Not recorded | 69df1b987d0172140ec7b92e | | ArcDeck | 82.4 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 75 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 67.91 | Not recorded | 69df1b987d0172140ec7b92e | | P2Poster | 60.8 | Not recorded | 69df1b987d0172140ec7b92e | | SlideGen | 60 | Not recorded | 69df1b987d0172140ec7b92e | | PPTAgent | 59.04 | Not recorded | 69df1b987d0172140ec7b92e | | HTML | 51.36 | Not recorded | 69df1b987d0172140ec7b92e | ### SlideGen Story Accuracy: 97.6. Result ID: 69df404547f34ce924c7b7ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### ArcDeck Story Accuracy: 96. Result ID: 69df404547f34ce924c7b7af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### HTML Story Accuracy: 95.6. Result ID: 69df404547f34ce924c7b7ab. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### ArcDeck Story Accuracy: 93.12. Result ID: 69df404547f34ce924c7b7b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### SlideGen Story Accuracy: 90.42. Result ID: 69df404547f34ce924c7b7b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### P2Poster Story Accuracy: 87. Result ID: 69df404547f34ce924c7b7ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### P2Poster Story Accuracy: 86.14. Result ID: 69df404547f34ce924c7b7b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### HTML Story Accuracy: 85.67. Result ID: 69df404547f34ce924c7b7b5. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### ArcDeck Story Accuracy: 82.4. Result ID: 69df404547f34ce924c7b7b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### PPTAgent Story Accuracy: 75. Result ID: 69df404547f34ce924c7b7ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction. ### PPTAgent Story Accuracy: 67.91. Result ID: 69df404547f34ce924c7b7b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction. ### P2Poster Story Accuracy: 60.8. Result ID: 69df404547f34ce924c7b7b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### SlideGen Story Accuracy: 60. Result ID: 69df404547f34ce924c7b7b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### PPTAgent Story Accuracy: 59.04. Result ID: 69df404547f34ce924c7b7b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. ### HTML Story Accuracy: 51.36. Result ID: 69df404547f34ce924c7b7b0. [Reporting paper]() Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.