# VLM-based Q/A Quiz on ArcBench VLM-based Q/A Quiz Open

Source: [VLM-based Q/A Quiz on ArcBench VLM-based Q/A Quiz Open](<https://www.sota2.com/research/sota/vlm-based-q-a-quiz-on-arcbench-vlm-based-q-a-quiz-open>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T07:42:16.385Z

Evaluation of model performance on the ArcBench VLM-based Q/A Quiz Open dataset for VLM-based Question Answering, reporting metrics across Story, Visuals, Hard, and Depth categories.

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 Open |
| Metric | Accuracy (Story) |
| 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

- [Accuracy (Story)](<https://www.sota2.com/research/sota/vlm-based-q-a-quiz-on-arcbench-vlm-based-q-a-quiz-open.md?metric=Accuracy%20(Story)>): Higher is better; unit: PERCENT.

- [Accuracy (Visuals)](<https://www.sota2.com/research/sota/vlm-based-q-a-quiz-on-arcbench-vlm-based-q-a-quiz-open.md?metric=Accuracy%20(Visuals)>): Higher is better; unit: PERCENT.

- [Accuracy (Hard)](<https://www.sota2.com/research/sota/vlm-based-q-a-quiz-on-arcbench-vlm-based-q-a-quiz-open.md?metric=Accuracy%20(Hard)>): Higher is better; unit: PERCENT.

- [Accuracy (Depth)](<https://www.sota2.com/research/sota/vlm-based-q-a-quiz-on-arcbench-vlm-based-q-a-quiz-open.md?metric=Accuracy%20(Depth)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Story) | Result date | Report paper |
| --- | --- | --- | --- |
| ArcDeck | 95.69 | Not recorded | 69df1b987d0172140ec7b92e |
| ArcDeck | 95.46 | Not recorded | 69df1b987d0172140ec7b92e |
| ArcDeck | 95.41 | Not recorded | 69df1b987d0172140ec7b92e |
| SlideGen | 95.26 | Not recorded | 69df1b987d0172140ec7b92e |
| P2Poster | 95.22 | Not recorded | 69df1b987d0172140ec7b92e |
| HTML | 95.16 | Not recorded | 69df1b987d0172140ec7b92e |
| SlideGen | 94.81 | Not recorded | 69df1b987d0172140ec7b92e |
| P2Poster | 94.28 | Not recorded | 69df1b987d0172140ec7b92e |
| P2Poster | 94.12 | Not recorded | 69df1b987d0172140ec7b92e |
| HTML | 94.07 | Not recorded | 69df1b987d0172140ec7b92e |
| SlideGen | 93.75 | Not recorded | 69df1b987d0172140ec7b92e |
| PPTAgent | 93.35 | Not recorded | 69df1b987d0172140ec7b92e |
| HTML | 93.34 | Not recorded | 69df1b987d0172140ec7b92e |
| PPTAgent | 92.96 | Not recorded | 69df1b987d0172140ec7b92e |
| PPTAgent | 92.66 | Not recorded | 69df1b987d0172140ec7b92e |

### ArcDeck

Accuracy (Story): 95.69. Result ID: 69df404547f34ce924c7b7aa.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Implementation](<https://github.com/RehgLab/ArcDeck>)

Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction.

### ArcDeck

Accuracy (Story): 95.46. Result ID: 69df404547f34ce924c7b7a5.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Implementation](<https://github.com/RehgLab/ArcDeck>)

Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction.

### ArcDeck

Accuracy (Story): 95.41. Result ID: 69df404547f34ce924c7b7a0.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Implementation](<https://github.com/RehgLab/ArcDeck>)

Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction.

### SlideGen

Accuracy (Story): 95.26. Result ID: 69df404547f34ce924c7b79f.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326754d6b0dd334293454c.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction.

### P2Poster

Accuracy (Story): 95.22. Result ID: 69df404547f34ce924c7b79d.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d11e209131cea7a94a.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction.

### HTML

Accuracy (Story): 95.16. Result ID: 69df404547f34ce924c7b79c.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction.

### SlideGen

Accuracy (Story): 94.81. Result ID: 69df404547f34ce924c7b7a9.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326754d6b0dd334293454c.md>)

Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction.

### P2Poster

Accuracy (Story): 94.28. Result ID: 69df404547f34ce924c7b7a7.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d11e209131cea7a94a.md>)

Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction.

### P2Poster

Accuracy (Story): 94.12. Result ID: 69df404547f34ce924c7b7a2.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d11e209131cea7a94a.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction.

### HTML

Accuracy (Story): 94.07. Result ID: 69df404547f34ce924c7b7a6.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction.

### SlideGen

Accuracy (Story): 93.75. Result ID: 69df404547f34ce924c7b7a4.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326754d6b0dd334293454c.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction.

### PPTAgent

Accuracy (Story): 93.35. Result ID: 69df404547f34ce924c7b7a3.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770b1e209131cea70b57.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction.

### HTML

Accuracy (Story): 93.34. Result ID: 69df404547f34ce924c7b7a1.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-4o"}. This record does not assert independent reproduction.

### PPTAgent

Accuracy (Story): 92.96. Result ID: 69df404547f34ce924c7b79e.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770b1e209131cea70b57.md>)

Recorded evaluation configuration: {"Generation Model":"GPT-5"}. This record does not assert independent reproduction.

### PPTAgent

Accuracy (Story): 92.66. Result ID: 69df404547f34ce924c7b7a8.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b987d0172140ec7b92e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770b1e209131cea70b57.md>)

Recorded evaluation configuration: {"Generation Model":"Qwen-3-VL-32B-Instruct"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
