AgroVG: leaderboard
Visual grounding, the task of localizing objects described by natural-language expressions, is a foundational capability for agricultural AI systems, enabling applications such as selective weeding, disease monitoring, and targeted harvesting. Reliable evaluation of agricultural visual grounding remains challenging because agricultural targets are often small, repetitive, occluded, or irregularly
Metric: All@.5 (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 27.36 | #79 |
| 2 | Claude Sonnet 4.6 | 19.95 | #90 |
| 3 | Gemini 2.5 Pro | 18.49 | #152 |
| 4 | GPT-4o | 15.05 | #343 |
Interactive version: theaggregate.ai/benchmark?slug=agrovg · How It Works · Data refreshed daily, snapshot 2026-10-20.