VLM-based Q/A Quiz on ArcBench VLM-based Q/A Quiz Closed
97.6Story AccuracySlideGen
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SlideGenGeneration Model=GPT-52026.04 | 97.6 | 35.8 | 86 | 82.4 | |
| ArcDeckGeneration Model=GPT-52026.04 | 96 | 41 | 85.6 | 83.4 | |
| HTMLGeneration Model=GPT-52026.04 | 95.6 | 38.4 | 80 | 82.2 | |
| ArcDeckGeneration Model=Qwen-3-VL-32B-Instruct2026.04 | 93.12 | 34.79 | 68.28 | 66.7 | |
| SlideGenGeneration Model=Qwen-3-VL-32B-Instruct2026.04 | 90.42 | 28.47 | 64.93 | 63.07 | |
| P2PosterGeneration Model=GPT-52026.04 | 87 | 27 | 66.4 | 64.6 | |
| P2PosterGeneration Model=Qwen-3-VL-32B-Instruct2026.04 | 86.14 | 21.49 | 51.26 | 54.51 | |
| HTMLGeneration Model=Qwen-3-VL-32B-Instruct2026.04 | 85.67 | 36.65 | 63.26 | 61.77 | |
| ArcDeckGeneration Model=GPT-4o2026.04 | 82.4 | 18.16 | 40.08 | 47.2 | |
| PPTAgentGeneration Model=GPT-52026.04 | 75 | 12.8 | 32 | 36.2 | |
| PPTAgentGeneration Model=Qwen-3-VL-32B-Instruct2026.04 | 67.91 | 12 | 22.14 | 25.12 | |
| P2PosterGeneration Model=GPT-4o2026.04 | 60.8 | 8.16 | 17.6 | 20.24 | |
| SlideGenGeneration Model=GPT-4o2026.04 | 60 | 8.08 | 17.84 | 21.36 | |
| PPTAgentGeneration Model=GPT-4o2026.04 | 59.04 | 7.52 | 15.12 | 18.56 | |
| HTMLGeneration Model=GPT-4o2026.04 | 51.36 | 6.64 | 11.84 | 14.16 |