List your company

Question Answering on TimelineQA (test)

36.9Hit@1RAG
12.56418.88225.231.518May 17, 2025

Evaluation results

MethodLinks
RAGModel=LLaMA3.3 (70B)2025.0536.941
REQAPModel=GPT4o (>100B)2025.0535.739
RAGModel=GPT4o (>100B)2025.0532.136
REQAPModel=SFT (1B)2025.0531.335
REQAPModel=LLaMA3.3 (70B)2025.0528.631
CODEGENModel=GPT4o (>100B)2025.0526.233
RAGModel=SFT (1B)2025.0521.422
CODEGENModel=LLaMA3.3 (70B)2025.0518.722
CODEGENModel=SFT (1B)2025.0513.517