PlantMicro - Counting (Multiple Choice): leaderboard
Counting in PlantMicro (2026), a benchmark of vision-language models on microscopic plant images: accuracy in percent at choosing the number of target instances among the true count and nearby integers, zero-shot. Higher is better.
Metric: Counting accuracy (%) when choosing the number of target instances among the true count and nearby integer distractors on microscopic plant images; zero-shot. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 71.34 | #167 |
| 2 | GPT-5 Mini | 66.29 | #348 |
| 3 | Gemini 2.5 Pro | 41.37 | #266 |
| 4 | Gemini 2.5 Flash | 40.62 | #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-counting-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-11-13.