StressWeb - Layout Chaos: leaderboard
StressWeb (2026) is a diagnostic stress test for web agents: generated websites with clean reference workflows are re-run under controlled perturbations, and deterministic scripts check task checkpoints on the recorded page states. This board is the checkpoint pass rate in percent under visual layout perturbation; higher is better.
Metric: Checkpoint pass rate (%): share of predefined task checkpoints (milestones such as reaching a target page or completing required fields) that the agent's run passes, under visual layout perturbation (altered text size, rotated and shifted elements), on 149 tasks over 10 generated websites, a multimodal agent driving a Playwright controller from screenshots, the page DOM and its action history (100-step budget), checkpoints verified by task-specific scripts on the recorded DOM states; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O4 Mini | 54.8 | #368 |
| 2 | Gemini 2.5 Pro | 53.7 | #276 |
| 3 | GPT-5.2 | 49.1 | #185 |
| 4 | Claude Sonnet 4.5 | 45.7 | #261 |
| 5 | Qwen 3 VL 235B A22B (Thinking) | 44.9 | #459 |
| 6 | Claude Opus 4.5 | 41.6 | #160 |
| 7 | Claude Haiku 4.5 | 38.5 | #583 |
| 8 | GLM-4.6V | 38.3 | #710 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=stressweb-layout-chaos · How It Works · Data refreshed daily, snapshot 2026-11-21.