UXBench - Human-Rated Lift: leaderboard
Metric: Mean repair lift (rubric points on the 1-5 scale, signed): blind ratings by six UX and front-end experts of the fixture repaired from the model's UX report minus the unrepaired baseline, paired by site over the 41 fixtures and averaged over seven rubric dimensions; the model explores each fixture through a coverage-gated browser trajectory and a fixed repair agent applies its report; higher is better. Source: arxiv.org. Saturation forecast: Around 2032. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 0.35 |
| 2 | Claude Sonnet 4.6 | 0.32 |
| 3 | GPT-5.4 Mini | 0.26 |
| 4 | GLM-5.1 | 0.25 |
| 5 | Gemini 3.1 Pro (Preview) | 0.21 |
| 6 | Kimi K2.5 | 0.21 |
| 7 | GPT-5.4 Nano | 0.2 |
| 8 | Qwen 3.6 Plus | 0.17 |
Interactive version: theaggregate.ai/benchmark?slug=uxbench-human-rated-lift · How It Works · Data refreshed daily, snapshot 2026-09-29.