WebForge-Bench (DOM Only): leaderboard
WebForge-Bench (2026) tests browser agents on tasks set in automatically generated, reproducible websites with injected real-web noise, controlled for difficulty along seven dimensions. This board is task accuracy in percent over all tasks when the agent receives only the page DOM, without screenshots; higher is better.
Metric: Accuracy (%) over all 934 WebForge-Bench tasks on generated, self-contained websites with injected real-web noise, up to 50 browser actions, final-state answer checking; DOM-only setting: the agent receives the page DOM without screenshots (text-only models, and multimodal models with screenshots removed); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 59.2 | #145 |
| 2 | Gemini 3 Flash | 51.2 | #175 |
| 3 | GLM-4.7 | 50.2 | #380 |
| 4 | DeepSeek V3.2 | 48.8 | #419 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=webforge-bench-dom-only · How It Works · Data refreshed daily, snapshot 2026-11-21.