List your company

All tasks combined on AOP-Wiki structured question answering set (test)

100AccuracyDeepSeek
11.634.5557.580.45Apr 13, 2026

Evaluation results

MethodLinks
DeepSeekRAG enhancement=W/ RAG2026.04100
OverallRAG enhancement=W/ RAG2026.0496.67
GeminiRAG enhancement=W/ RAG2026.0495
GPTRAG enhancement=W/ RAG2026.0495
DeepSeekRAG enhancement=W/O RAG2026.0435
OverallRAG enhancement=W/O RAG2026.0423.33
GeminiRAG enhancement=W/O RAG2026.0420
GPTRAG enhancement=W/O RAG2026.0415