AgroTools - Summary Accuracy: leaderboard
Step-by-step mode on AgroTools (2026), image-grounded agricultural questions (pest and disease diagnosis, counting and measurement, change detection, visualization) with 14 executable agricultural tools: given the gold history, the similarity of the final answer to the reference at gold answer steps, with penalties for numeric inconsistency and missing content, scaled to 0-100; higher is better.
Metric: Summary accuracy (0-100): normalized similarity of the final answer to the reference at gold answer steps, with penalties for numeric inconsistency and missing key content and zero when the model calls a tool instead of answering, in step-by-step mode on AgroTools (539 image-grounded agricultural queries with human-specified, human-audited reference tool trajectories over 14 executable tools; the model predicts the next step given the gold history), Lagent ReAct schema, temperature 0.1; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3.5-14B | 33.96 | #1504 |
| 2 | InternVL3.5-8B | 33.72 | #1604 |
| 3 | Qwen 3 VL 8B Instruct | 28.24 | #1029 |
| 4 | Claude Sonnet 4.6 | 25.53 | #173 |
| 5 | GLM-4.6V | 22.48 | #710 |
| 6 | LLaVA-v1.6-Vicuna-13B | 21.83 | #5527 |
| 7 | Gemini 2.5 Pro | 21.01 | #276 |
| 8 | InternVL3-8B | 20.52 | #1782 |
| 9 | Seed 2.0 Pro | 17.52 | #222 |
| 10 | Qwen 3.5 9B | 16.7 | #828 |
| 11 | Qwen 3.5 35B A3B | 13.88 | #492 |
| 12 | GPT-5.4 | 10.93 | #135 |
| 13 | Janus-Pro-7B | 1.34 | #6857 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=agrotools-summary-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-21.