ComponentBench (Browser Use): leaderboard
Metric: Pass rate (%; share of tasks whose programmatic verifier passes; the browser-use agent framework with screenshots, serialized DOM and grounded element references, up to 4 actions per step; ComponentBench-Full: 2,910 programmatically verified tasks on 97 canonical UI components across widely used web component libraries; 20-step budget; one deterministic run). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Browser Use + Gemini 3 Flash | 95.2 |
| 2 | Browser Use + GPT-5.4 | 90.4 |
| 3 | Browser Use + Gemini 3.1 Flash-Lite | 87.4 |
| 4 | Browser Use + GPT-5 mini | 87 |
| 5 | Browser Use + GPT-5.4 mini | 85.8 |
| 6 | Browser Use + Qwen3-VL-235B | 78.8 |
Interactive version: theaggregate.ai/benchmark?slug=componentbench-browser-use · How It Works · Data refreshed daily, snapshot 2026-09-29.