WebIGBench (Direct Prompt): leaderboard
WebIGBench (Wu et al., 2026) asks multimodal models to write a single-file interactive webpage from screenshots of a real site (103 pages from 15 categories, 871 annotated interactions), and a browser-use UI agent then replays the reference interaction path on the generated page. Success rate in percent, counting pages where the agent reaches the final step within twice the reference number of steps; higher is better. This board uses the Direct prompt (screenshots and textual instructions), temperature 0.
Metric: Success rate (%; the UI agent replays the reference interaction on the generated page and reaches the final step within twice the reference steps, 103 webpages, screenshots and textual instructions). Source: arxiv.org. Saturation forecast: Around July 2028. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 52.43 | #262 |
| 2 | Qwen-VL-Max | 34.95 | #1226 |
| 3 | GPT-5 | 31.07 | #163 |
| 4 | Grok 4 | 23.3 | #306 |
| 5 | GLM-4.5V | 23.3 | #739 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=webigbench-direct-prompt · How It Works · Data refreshed daily, snapshot 2026-11-12.