LivingScreen: leaderboard
Metric: Success rate (%), mean of the three task tiers; LivingScreen: 499 Chinese short-video tasks in a browser replica of a short-video app (1,528 real videos, about 5.6 per feed); a single-agent loop issues GUI actions plus watch and wait primitives from screenshots or recorded clips, 30-step cap, temperature 0.6, high reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash (High) | 69.3 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 66.2 |
| 3 | Seed 2.0 Pro (High) | 64.8 |
| 4 | Claude Opus 4.6 (High) | 45.6 |
| 5 | GLM-5V Turbo | 42.7 |
| 6 | Claude Sonnet 4.6 (High) | 38.7 |
| 7 | Kimi K2.5 (Thinking) | 36.8 |
| 8 | GPT-5.5 (High) | 29.8 |
| 9 | GPT-5.4 (High) | 25.2 |
Interactive version: theaggregate.ai/benchmark?slug=livingscreen · How It Works · Data refreshed daily, snapshot 2026-09-29.