Target Recognition on CFMS
82.54Target AccuracyGemini-2.5-Flash
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-FlashPrompting Strategy=Zero-shot2026.03 | 82.54 | |
| Gemini-2.5-FlashPrompting Strategy=RAG 1-shot2026.03 | 80.42 | |
| Gemini-2.5-FlashPrompting Strategy=Random 1-shot2026.03 | 76.19 | |
| GPT-4oPrompting Strategy=RAG 1-shot2026.03 | 73.02 | |
| GPT-4oPrompting Strategy=Zero-shot2026.03 | 71.03 | |
| GPT-4oPrompting Strategy=Random 1-shot2026.03 | 61.17 | |
| LoRA FTModel=InternVL2.5-8B2026.03 | 53.48 | |
| InternVL2.5-8BPrompting Strategy=PGDS2026.03 | 50.89 | |
| LoRA FTModel=Qwen2.5-VL-7B-Instruct2026.03 | 49.73 | |
| Qwen2.5-VL-7B-InstructPrompting Strategy=PGDS2026.03 | 48.68 | |
| InternVL2.5-8BPrompting Strategy=Random 1-shot2026.03 | 48.15 | |
| InternVL2.5-8BPrompting Strategy=RAG 1-shot2026.03 | 46.15 | |
| Qwen2.5-VL-7B-InstructPrompting Strategy=RAG 1-shot2026.03 | 45.67 | |
| InternVL2.5-8BPrompting Strategy=Zero-shot2026.03 | 40.47 | |
| Qwen2.5-VL-7B-InstructPrompting Strategy=Random 1-shot2026.03 | 38.62 | |
| LoRA FTModel=LLaVA-1.5-7B2026.03 | 36.51 | |
| Qwen2.5-VL-7B-InstructPrompting Strategy=Zero-shot2026.03 | 32.54 |