LiveWeb-IE: leaderboard
Metric: Overall F1 (%) of extracted values over all task types of LiveWeb-IE (live websites in 15 domains): the model writes reusable XPath wrappers from the first page of each page group, given its HTML and a natural-language query, and the wrappers extract values from every page of the group on the live site; attributes are aligned by a GPT-4o matcher; single-pass chain-of-thought generation; higher is better. Source: arxiv.org. Saturation forecast: Around October 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 24.6 | #333 |
| 2 | Qwen 2.5 72B Instruct | 22.06 | #436 |
| 3 | GPT-4o Mini | 20.63 | #588 |
| 4 | Gemini 2.5 Flash | 20.53 | #237 |
| 5 | Qwen 2.5 32B Instruct | 17.74 | #491 |
| 6 | Gemma 3 27B (IT) | 16.65 | #509 |
| 7 | Qwen 2.5 7B Instruct | 11.67 | #846 |
| 8 | Gemma 3 4B (IT) | 5.98 | #971 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=liveweb-ie · How It Works · Data refreshed daily, snapshot 2026-10-11.