LLM Agronomy Benchmark (FBN) - Soil and Water: leaderboard
Farmers Business Network LLM Agronomy Benchmark (Soil and Water) measuring multiple-choice accuracy (%) on private agronomy text and image tasks.
Metric: Category Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 110 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 97.5 | #18 |
| 2 | Grok 4.5 | 96.2 | #91 |
| 3 | Muse Spark Open | 96.2 | #82 |
| 4 | GPT-5.5 | 95 | #56 |
| 5 | Claude Opus 4.8 | 95 | #64 |
| 6 | Gemini 3.8 Flash | 95 | #43 |
| 7 | GPT-6 Astra | 95 | #11 |
| 8 | O3 | 95 | #242 |
| 9 | MiniMax-M2.5 | 95 | #600 |
| 10 | Grok 4.7 | 95 | #55 |
| 11 | GPT-5.3 Codex | 95 | #125 |
| 12 | Muse Wonder | 95 | #34 |
| 13 | GPT-5.6 Pro Terra | 95 | #53 |
| 14 | Gemini 3.1 Pro (Preview) (Tools: Custom) | 95 | #99 |
| 15 | Gemini 3.1 Pro (Preview) | 93.8 | #102 |
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-soil-and-water · How It Works · Data refreshed daily, snapshot 2026-11-22.