AgroTools - Argument 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 share of gold tool-call steps where the model calls the reference tool with valid arguments that match the reference. Percent; higher is better.
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 February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 2.0 Pro | 49.34 | #226 |
| 2 | Gemini 2.5 Pro | 47.06 | #280 |
| 3 | Qwen 3.5 35B A3B | 40.7 | #494 |
| 4 | GLM-4.6V | 39.53 | #721 |
| 5 | InternVL3.5-14B | 32.27 | #1519 |
| 6 | InternVL3.5-8B | 31.58 | #1618 |
| 7 | Qwen 3.5 9B | 27.44 | #838 |
| 8 | GPT-5.4 | 26.26 | #138 |
| 9 | Qwen 3 VL 8B Instruct | 23.43 | #1043 |
| 10 | Claude Sonnet 4.6 | 23.15 | #179 |
| 11 | LLaVA-v1.6-Vicuna-13B | 5.46 | #5573 |
| 12 | InternVL3-8B | 5.32 | #1795 |
| 13 | Janus-Pro-7B | 0.21 | #6889 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=agrotools-argument-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-22.