PlantXpert - Cotton: leaderboard

PlantXpert (2026) is an evidence-grounded multimodal benchmark for soybean and cotton phenotyping: four-option questions built on figures, captions and text from plant science publications, evaluated on the expert-annotated Gold split with chain-of-thought prompting. This board is accuracy in percent on the cotton questions; higher is better.

Metric: Accuracy (%) on the 73 cotton questions on the expert-annotated PlantXpert Gold split (369 four-option questions on soybean and cotton figures from plant science publications), base checkpoints with chain-of-thought prompting, temperature 0, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 VL 8B79.45#917
2Qwen 3 VL 30B A3B78.08#784
3Gemma 3 27B76.71#1663
4Qwen 3 VL 4B75.34#1151
5InternVL3.5-2B71.23#3284
6Gemma 3 12B68.49#2059
7Qwen 3 VL 2B64.38#2134
8LLaVA-NeXT-34B63.01#3443
9Gemma 3 4B57.53#5339
10LLaVA-Next-LLaMA3-8B53.42#5654
11Granite-Vision-3.3-2B52.05#6934

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=plantxpert-cotton · How It Works · Data refreshed daily, snapshot 2026-11-21.