TVWorld-G: leaderboard
Metric: Acc@0.5 (%; predicted focused-element box with IoU of at least 0.5, 187 Google TV screenshots). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 78.1 |
| 2 | Qwen 3 VL 8B (Thinking) | 69.5 |
| 3 | Qwen 2.5 VL 7B Instruct | 66.3 |
Interactive version: theaggregate.ai/benchmark?slug=tvworld-g · How It Works · Data refreshed daily, snapshot 2026-09-25.