VTB — leaderboard
Evaluating how LLMs can dynamically interact with and reason about visual information.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 29.17 |
| 2 | Gemini 3.1 Pro (Preview) | 28.97 |
| 3 | Claude Opus 4.6 | 27.52 |
| 4 | GPT-5 | 18.68 |
| 5 | O3 | 13.74 |
| 6 | Gemini 2.5 Pro (Preview 06-05) | 11.75 |
| 7 | O4 Mini | 11.12 |
| 8 | Claude Sonnet 4.5 | 6.2 |
| 9 | GPT-4.1 | 5.52 |
| 10 | Claude Opus 4.1 | 5.16 |
| 11 | Gemini 2.5 Flash | 4.69 |
| 12 | Claude Sonnet 4 | 4.48 |
| 13 | Claude Sonnet 4 (Thinking) | 4.44 |
| 14 | Nova Premier | 2 |
| 15 | Llama 4 Maverick | 1.41 |
Interactive version: theaggregate.ai/benchmark?slug=vtb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.