PlantXpert - Remote Sensing and Imaging: 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 remote sensing and imaging questions; higher is better.

Metric: Accuracy (%) on the remote sensing and imaging domain 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 30B A3B90.91#784
2Qwen 3 VL 4B86.36#1151
3Granite-Vision-3.3-2B81.82#6934
4Qwen 3 VL 8B77.27#917
5InternVL3.5-2B77.27#3284
6Gemma 3 12B68.18#2059
7LLaVA-NeXT-34B68.18#3443
8Gemma 3 27B63.64#1663
9Gemma 3 4B59.09#5339
10LLaVA-Next-LLaMA3-8B59.09#5654
11Qwen 3 VL 2B54.55#2134

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

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