PlantMicro - Localization (Multiple Choice): leaderboard
Localization in PlantMicro (2026), a benchmark of vision-language models on microscopic plant images: accuracy in percent at choosing the true bounding box among spatially shifted candidates, zero-shot. Higher is better.
Metric: Localization accuracy (%) when choosing the true bounding box among non-overlapping, spatially shifted candidate boxes of similar size; zero-shot. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 83.21 | #167 |
| 2 | GPT-5 Mini | 79.33 | #348 |
| 3 | Gemini 2.5 Pro | 65.91 | #266 |
| 4 | Gemini 2.5 Flash | 62.77 | #453 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=plantmicro-localization-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-11-13.