Web Information Extraction on LIVEWEB-IE Type III 1.0 (test)
89.3PrecisionHuman
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Human2026.03 | 89.3 | 89.5 | 89.04 | |
| VGSModel=GPT -4o2026.03 | 45.25 | 45.73 | 45.38 | |
| VGSModel=Gemini-2.5-Flash2026.03 | 43.61 | 43.49 | 42.92 | |
| VGSModel=Qwen-2.5-72B2026.03 | 35.3 | 39.43 | 36.53 | |
| VGSModel=GPT -4o-mini2026.03 | 33.87 | 34.58 | 33.95 | |
| VGSModel=Qwen-2.5-32B2026.03 | 30.33 | 30.61 | 29.9 | |
| VGSModel=Gemma-3-27B2026.03 | 27.9 | 31.82 | 29.73 | |
| VGSModel=Qwen-2.5-7B2026.03 | 16.63 | 18.39 | 16.64 | |
| ReflexionModel=GPT -4o2026.03 | 15.99 | 10.34 | 10.24 | |
| VGSModel=Gemma-3-4B2026.03 | 15.02 | 24.92 | 15.7 | |
| AutoScraperModel=GPT -4o2026.03 | 13.95 | 12.1 | 9.1 | |
| COTModel=GPT -4o2026.03 | 12.14 | 11.44 | 8.15 | |
| AutoScraperModel=GPT -4o-mini2026.03 | 11.74 | 19.26 | 11.05 | |
| AutoScraperModel=Gemini-2.5-Flash2026.03 | 10.94 | 18.61 | 10.23 | |
| ReflexionModel=Qwen-2.5-72B2026.03 | 10.69 | 8.96 | 8.42 | |
| ReflexionModel=Gemini-2.5-Flash2026.03 | 10.29 | 13 | 8.3 | |
| ReflexionModel=Gemma-3-27B2026.03 | 10.16 | 17.95 | 12.03 | |
| AutoScraperModel=Qwen-2.5-72B2026.03 | 10.05 | 18.33 | 8.62 | |
| AutoScraperModel=Gemma-3-27B2026.03 | 9.81 | 16.58 | 10.27 | |
| AutoScraperModel=Gemma-3-4B2026.03 | 9.67 | 35.85 | 10.27 | |
| COTModel=Gemini-2.5-Flash2026.03 | 9.66 | 13.99 | 8.19 | |
| ReflexionModel=Gemma-3-4B2026.03 | 9.57 | 32.23 | 10.99 | |
| COTModel=Gemma-3-27B2026.03 | 9.56 | 17.39 | 10.69 | |
| COTModel=Qwen-2.5-72B2026.03 | 9.48 | 19.62 | 7.53 | |
| COTModel=GPT -4o-mini2026.03 | 8.88 | 18.45 | 8.76 | |
| ReflexionModel=Qwen-2.5-32B2026.03 | 8.47 | 15.02 | 6.72 | |
| ReflexionModel=GPT -4o-mini2026.03 | 8.26 | 9.09 | 7.6 | |
| AutoScraperModel=Qwen-2.5-7B2026.03 | 7.35 | 11.64 | 7.5 | |
| COTModel=Qwen-2.5-32B2026.03 | 7.2 | 16.11 | 6.23 | |
| AutoScraperModel=Qwen-2.5-32B2026.03 | 7.11 | 14.63 | 8.37 | |
| ReflexionModel=Qwen-2.5-7B2026.03 | 5.64 | 23.71 | 7.76 | |
| COTModel=Gemma-3-4B2026.03 | 5.63 | 7.22 | 5.9 | |
| COTModel=Qwen-2.5-7B2026.03 | 4.37 | 15.85 | 4.98 |