LeafBench - Symptom Identification: leaderboard
Metric: Accuracy (%) on the questions asking the visible symptom (spots, pustules, chlorosis and others), on the full LeafBench set (13,950 label-constrained multiple-choice questions on 2,570 leaf images from the LeafNet plant-disease dataset, 22 crop species and 62 diseases); zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 51.64 | #333 |
| 2 | Gemini 2.5 Pro | 48.99 | #145 |
| 3 | Qwen 2.5 VL 7B Instruct | 43.14 | #643 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=leafbench-symptom-identification · How It Works · Data refreshed daily, snapshot 2026-10-11.