List your company

Question Answering on NoisyRetrieval Level 2

100Exact Match AccuracyLLM-Discrim
92.7294.6196.598.39Feb 26, 2025

Evaluation results

MethodLinks
LLM-DiscrimModel=Llama3-8b-instruct2025.02100—
ENDModel=Llama3-8b-instruct2025.02100100
RAGModel=Qwen2.5-7b-instruct2025.02100—
ENDModel=Qwen2.5-7b-instruct2025.02100100
ENDModel=Mistral-v0.3-instruct2025.02100100
LLM-DiscrimModel=Qwen2.5-7b-instruct2025.0296—
RAGModel=Mistral-v0.3-instruct2025.0296—
RAGModel=Llama3-8b-instruct2025.0295—
LLM-DiscrimModel=Mistral-v0.3-instruct2025.0293—