List your company
ResearchFormerly WizWand

Question Answering on RealtimeQA

86.7AccuracyKRE
25.96441.73257.573.268Jun 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
KREBackbone LLM=qwen2.5-7b-instruct2025.0686.7
FaithfulRAGBackbone LLM=qwen2.5-7b-instruct2025.0684.1
ATTRBackbone LLM=qwen2.5-7b-instruct2025.0683
Opin(Instr)Backbone LLM=qwen2.5-7b-instruct2025.0681.4
FaithfulRAGBackbone LLM=llama3.1-8b-instruct2025.0681.4
COIECDBackbone LLM=qwen2.5-7b-instruct2025.0678.8
Origin model with full contextBackbone LLM=qwen2.5-7b-instruct2025.0678.7
CADBackbone LLM=qwen2.5-7b-instruct2025.0677
FaithfulRAGBackbone LLM=mistral-7b-instruct2025.0677
ATTRBackbone LLM=llama3.1-8b-instruct2025.0676.9
KREBackbone LLM=mistral-7b-instruct2025.0676.9
Opin(Instr)Backbone LLM=llama3.1-8b-instruct2025.0675.2
Origin model with full contextBackbone LLM=llama3.1-8b-instruct2025.0667.3
COIECDBackbone LLM=llama3.1-8b-instruct2025.0662.8
CADBackbone LLM=llama3.1-8b-instruct2025.0661.9
COIECDBackbone LLM=mistral-7b-instruct2025.0658.4
ChatQA-2.0Backbone LLM=Llama3.1-8B2025.0657.5
ChatQA-1.5Backbone LLM=Llama3.1-8B2025.0656.7
Self-RAGBackbone LLM=Llama2-7B2025.0655.8
CADBackbone LLM=mistral-7b-instruct2025.0655.8
Origin model with full contextBackbone LLM=mistral-7b-instruct2025.0652.2
ATTRBackbone LLM=mistral-7b-instruct2025.0652.2
Opin(Instr)Backbone LLM=mistral-7b-instruct2025.0651.3
KREBackbone LLM=llama3.1-8b-instruct2025.0648.6
Origin model without contextBackbone LLM=qwen2.5-7b-instruct2025.0640.7
Origin model without contextBackbone LLM=mistral-7b-instruct2025.0629.2
Origin model without contextBackbone LLM=llama3.1-8b-instruct2025.0628.3