PlantMicro - Pathogen: leaderboard
Pathogen identification in PlantMicro (2026), a benchmark of vision-language models on microscopic plant images: accuracy in percent on four-option multiple-choice questions, zero-shot. Higher is better.
Metric: Pathogen identification accuracy (%); four-option multiple choice on microscopic plant images (light, fluorescence and electron microscopy) with distractors drawn from the same metadata field; zero-shot, unified prompt. Source: arxiv.org. Saturation forecast: Around December 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini | 43.91 | #348 |
| 2 | GPT-5 | 42.71 | #167 |
| 3 | Gemini 2.5 Pro | 33.19 | #266 |
| 4 | Gemini 2.5 Flash Lite | 33.05 | #958 |
| 5 | Gemini 2.5 Flash | 32.67 | #453 |
| 6 | GPT-4o Mini | 29 | #1623 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=plantmicro-pathogen · How It Works · Data refreshed daily, snapshot 2026-11-13.