List your company

Image Classification on PCam (Task Utility %)

60.98Task Utilityclean RAG
-2.439214.025430.4946.9546May 11, 2026

Evaluation results

MethodLinks
clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.0560.98
LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0558.68
clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.0556.1
M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0554.88
LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0552.74
clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.0551.22
LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0549.88
M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0547.44
M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0547.38
w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.0543.44
clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.0531.7
LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.0530.78
M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.0529.04
w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.0521.22
w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.0513.14
LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.050.2
w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.050
w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.050
clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.050
M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.050