ComponentBench (Pixel): leaderboard
Metric: Pass rate (%; share of tasks whose programmatic verifier passes; screenshot only, actions by predicted coordinates, in the shared BrowserGym harness or, for UI-TARS-1.5-7B, its native pixel-only harness; 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: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 85.4 |
| 2 | GPT-5.4 | 83.8 |
| 3 | GPT-5.4 Mini | 77.1 |
| 4 | Gemini 3.1 Flash Lite | 63.3 |
| 5 | Qwen 3 VL 235B A22B | 50.5 |
| 6 | GPT-5 Mini | 48.9 |
| 7 | uitars-1.5-7B | 12.6 |
Interactive version: theaggregate.ai/benchmark?slug=componentbench-pixel · How It Works · Data refreshed daily, snapshot 2026-09-29.