List your company

Question Answering on PopQA (Accuracy (Acc))

70.7Accuracy (Acc)Qwen3-32B+Hit-RAG
14.33228.96643.658.234Mar 7, 2026

Evaluation results

MethodLinks
Qwen3-32B+Hit-RAGFramework=Hit-RAG2026.0370.7
Llama3.1-70B+R-InsRetrieval=Yes2026.0370.4
Llama3.1-8B+R-InsRetrieval=Yes2026.0368.4
Llama3.1-70B+Hit-RAGFramework=Hit-RAG2026.0366.7
RankRAG-70BRetrieval=Yes2026.0365.4
RankRAG-8BRetrieval=Yes2026.0364.1
Llama3.1-8B+Hit-RAGFramework=Hit-RAG2026.0363.6
Qwen3-8B+Hit-RAGFramework=Hit-RAG2026.0363.1
Qwen3-4B+Hit-RAGFramework=Hit-RAG2026.0360.8
RAS-7BRetrieval=Yes2026.0358.3
RAS-8BRetrieval=Yes2026.0357.7
Speculative RAG-7BRetrieval=Yes2026.0357.5
Self-Reasoning-13BRetrieval=Yes2026.0357.3
Self-RAG-13BRetrieval=Yes2026.0355.8
Self-RAG-7BRetrieval=Yes2026.0354.9
Self-Reasoning-7BRetrieval=Yes2026.0354.2
Ret-ChatGPTRetrieval=None2026.0350.8
Alpaca-13BRetrieval=Yes2026.0346.1
Llama3.1-70BRetrieval=None2026.0331.1
Sonnet-3.5Retrieval=None2026.0330.2
ChatGPTRetrieval=None2026.0329.3
Llama3.1-8BRetrieval=None2026.0328.8
Qwen3-32BRetrieval=None2026.0325.1
Alpaca-13BRetrieval=None2026.0324.4
Qwen3-8BRetrieval=None2026.0320.6
Qwen3-4BRetrieval=None2026.0316.5