Web UI Question Answering on VisualWebBench
67.3AccuracyDAVE
Evaluation Results
| Method | Links | |
|---|---|---|
| DAVELLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 67.3 | |
| SigLIP 2LLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 65.4 | |
| AIMv2LLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 64.9 | |
| DophineLLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 60.7 | |
| MAE-WebLLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 59.5 | |
| DAVELLM Backbone=Llama-3.2-3B-Instruct2025.12 | 59.2 | |
| SigLIP 2LLM Backbone=Llama-3.2-3B-Instruct2025.12 | 54.7 | |
| Pix2structLLM Backbone=Qwen-2.5-7B-Instruct2025.12 | 52.3 | |
| DophineLLM Backbone=Llama-3.2-3B-Instruct2025.12 | 48.8 | |
| AIMv2LLM Backbone=Llama-3.2-3B-Instruct2025.12 | 46.7 | |
| MAE-WebLLM Backbone=Llama-3.2-3B-Instruct2025.12 | 36.9 | |
| Pix2StructLLM Backbone=Llama-3.2-3B-Instruct2025.12 | 22.6 | |
| DinoV2LLM Backbone=Llama-3.2-3B-Instruct2025.12 | 13.2 | |
| DiTLLM Backbone=Llama-3.2-3B-Instruct2025.12 | 9.2 |