AgroTools - Argument Accuracy: leaderboard
Metric: Argument accuracy (%): share of gold tool-call steps where the model selects the reference tool with valid arguments matching the reference, 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 June 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.0 Pro | 49.34 |
| 2 | Gemini 2.5 Pro | 47.06 |
| 3 | Qwen 3.5 35B A3B | 40.7 |
| 4 | GLM-4.6V | 39.53 |
| 5 | Qwen 3.5 9B | 27.44 |
| 6 | GPT-5.4 | 26.26 |
| 7 | Qwen 3 VL 8B Instruct | 23.43 |
| 8 | Claude Sonnet 4.6 | 23.15 |
| 9 | InternVL3-8B | 5.32 |
Interactive version: theaggregate.ai/benchmark?slug=agrotools-argument-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-07.