LLM Agronomy Benchmark (FBN) - Image Weed: leaderboard

Farmers Business Network LLM Agronomy Benchmark (Image Weed) measuring multiple-choice accuracy (%) on private agronomy text and image tasks.

Metric: Image Identification Accuracy (%, 50 questions). Source: github.com. Saturation forecast: Around February 2027. 77 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.8 Flash94#43
2Gemini 3 Flash (Preview)92#156
3gemini-3.1-flash-image-preview90
4Gemini 3.1 Pro (Preview)84#102
5Gemini 4 Argon84#18
6Gemini 3.1 Flash Lite (Preview)82#419
7Gemini 3.1 Pro (Preview) (Tools: Custom)82#99
8Gemini 2.5 Pro80#280
9Kimi K380#62
10Muse Wonder80#34
11GPT-5.276#190
12Grok 4.576#91
13Grok 4.776#55
14GPT-5.574#56
15O374#242

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=llm-agronomy-benchmark-fbn-image-weed · How It Works · Data refreshed daily, snapshot 2026-11-22.