Image Classification on CRC100k
95.13Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 95.13 | |
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 95.13 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 91.41 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 91.41 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 87.84 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 85.82 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 85.82 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 84.98 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 80.61 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 65.95 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 63.42 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 59.58 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 54.29 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 48.94 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 48.07 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 46.66 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 46.61 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 45.39 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 21.27 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 12.38 |