Image-to-Web Conversion on IW-BENCH Medium
0.502Element AccuracyWebSight
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| WebSightChain-of-Thought (MCoT) status=Disabled2024.09 | 0.502 | 0.49 | |
| Qwen-VL-MaxChain-of-Thought (MCoT) status=Enabled, MCoT Hops=52024.09 | 0.472 | 0.46 | |
| GPT4VChain-of-Thought (MCoT) status=Enabled, MCoT Hops=52024.09 | 0.431 | 0.426 | |
| Gemini ProChain-of-Thought (MCoT) status=Enabled, MCoT Hops=52024.09 | 0.425 | 0.419 | |
| Claude 3 OpusChain-of-Thought (MCoT) status=Enabled, MCoT Hops=52024.09 | 0.378 | 0.372 | |
| Qwen-VL-MaxChain-of-Thought (MCoT) status=Disabled2024.09 | 0.369 | 0.353 | |
| Gemini ProChain-of-Thought (MCoT) status=Disabled2024.09 | 0.341 | 0.336 | |
| Claude 3 OpusChain-of-Thought (MCoT) status=Disabled2024.09 | 0.301 | 0.284 | |
| LLAVA-LLAMA-2-13BChain-of-Thought (MCoT) status=Enabled, MCoT Hops=52024.09 | 0.278 | 0.265 | |
| GPT4VChain-of-Thought (MCoT) status=Disabled2024.09 | 0.274 | 0.266 | |
| Qwen-VL-PlusChain-of-Thought (MCoT) status=Disabled2024.09 | 0.252 | 0.242 | |
| Qwen-VL-ChatChain-of-Thought (MCoT) status=Disabled2024.09 | 0.241 | 0.233 | |
| LLaVA-LLaMA-2-13BChain-of-Thought (MCoT) status=Disabled2024.09 | 0.189 | 0.181 | |
| MPLUG-OWL2Chain-of-Thought (MCoT) status=Disabled2024.09 | 0.146 | 0.132 | |
| miniGPT-4-LLaMA-2-7BChain-of-Thought (MCoT) status=Disabled2024.09 | 0.136 | 0.128 | |
| LLaMA-Adapter-V2-7BChain-of-Thought (MCoT) status=Disabled2024.09 | 0.043 | 0.044 |