AgroTools - Summary Accuracy: leaderboard
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.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 28.24 |
| 2 | Claude Sonnet 4.6 | 25.53 |
| 3 | GLM-4.6V | 22.48 |
| 4 | Gemini 2.5 Pro | 21.01 |
| 5 | InternVL3-8B | 20.52 |
| 6 | Seed 2.0 Pro | 17.52 |
| 7 | Qwen 3.5 9B | 16.7 |
| 8 | Qwen 3.5 35B A3B | 13.88 |
| 9 | GPT-5.4 | 10.93 |
Interactive version: theaggregate.ai/benchmark?slug=agrotools-summary-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-07.