Disease Classification on CDDMBench
33.7AccuracyAgri-CPJ (+ LLM-as-a-Judge)
Evaluation Results
| Method | Links | |
|---|---|---|
| Agri-CPJ (+ LLM-as-a-Judge)Model=GPT-5-Nano, Caption Generator=GPT-5-mini2026.04 | 33.7 | |
| Agri-CPJ (+ LLM-as-a-Judge)Model=GPT-5-Nano, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 32.8 | |
| Agri-CPJ (+ Caption (Optimized))Model=GPT-5-Nano, Caption Generator=GPT-5-mini2026.04 | 31.6 | |
| Agri-CPJ (+ Caption (Optimized))Model=GPT-5-Nano, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 31.4 | |
| Agri-CPJ (+ Few-shot)Model=GPT-5-Nano, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 31 | |
| Agri-CPJ (+ Few-shot)Model=GPT-5-Nano, Caption Generator=GPT-5-mini2026.04 | 29.8 | |
| Agri-CPJ (+ LLM-as-a-Judge)Model=Qwen-VL-Chat, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 25.39 | |
| Agri-CPJ (+ Few-shot)Model=Qwen-VL-Chat, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 24.49 | |
| Agri-CPJ (+ LLM-as-a-Judge)Model=Qwen-VL-Chat, Caption Generator=GPT-5-mini2026.04 | 14.8 | |
| Agri-CPJ (+ Few-shot)Model=Qwen-VL-Chat, Caption Generator=GPT-5-mini2026.04 | 14.5 | |
| Agri-CPJ (+ Caption (Optimized))Model=Qwen-VL-Chat, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 12.1 | |
| Zero-shot (Our Baseline)Model=GPT-5-Nano, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 11 | |
| Zero-shot (Our Baseline)Model=GPT-5-Nano, Caption Generator=GPT-5-mini2026.04 | 11 | |
| Agri-CPJ (+ Caption (Optimized))Model=Qwen-VL-Chat, Caption Generator=GPT-5-mini2026.04 | 7.17 | |
| Zero-shot (Our Baseline)Model=Qwen-VL-Chat, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 5.8 | |
| Zero-shot (Liu et al., 2024) BaselineModel=Qwen-VL-Chat, Caption Generator=Qwen2.5-VL-72B-Instruct2026.04 | 5 |