AgroTools - Tool Selection Accuracy: leaderboard
Metric: Tool accuracy (%): share of gold tool-call steps where the model calls a tool and selects the reference tool, 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: Around January 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.0 Pro | 95.16 |
| 2 | Gemini 2.5 Pro | 91.91 |
| 3 | Qwen 3.5 35B A3B | 91.71 |
| 4 | Qwen 3.5 9B | 86.66 |
| 5 | GLM-4.6V | 84.93 |
| 6 | Qwen 3 VL 8B Instruct | 67.31 |
| 7 | GPT-5.4 | 52.32 |
| 8 | Claude Sonnet 4.6 | 50.79 |
| 9 | InternVL3-8B | 20.66 |
Interactive version: theaggregate.ai/benchmark?slug=agrotools-tool-selection-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-07.