TVWorld-N: leaderboard
Metric: Success Rate (%; 500 tasks: 5 Google TV graphs x 50 start-goal pairs x text and image goals). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 66.4 |
| 2 | GPT-5 Mini | 60.2 |
| 3 | Qwen 3 VL 32B Instruct | 39 |
| 4 | Claude Haiku 4.5 | 25.4 |
| 5 | Qwen 3 VL 8B Instruct | 20 |
| 6 | uitars-1.5-7B | 1.6 |
Interactive version: theaggregate.ai/benchmark?slug=tvworld-n · How It Works · Data refreshed daily, snapshot 2026-09-25.