Our new X account is live! Follow @wizwand_team for updates

Noisy-RAG Question Answering on CoQA

92.4Exact Match (EM)

Qwen2.5-OpAmp-72B

Updated 4d ago

Evaluation Results

Method	Links
Qwen2.5-OpAmp-72B 2025.02		92.4
GPT-4o-0806 2025.02		88.6
DeepSeek-V3 2025.02		88.4
Llama3.3-70B-inst 2025.02		88.2
Qwen2.5-72B-inst 2025.02		85.8
Llama3.1-OpAmp-8B 2025.02		85.4
Qwen2.5-7B-inst 2025.02		84.2
Llama3.1-8B-inst 2025.02		82.2
Llama3-ChatQA2-70B 2025.02		80.2
Llama3-ChatQA2-8B 2025.02		78.2
Mistral-7B-inst-v0.3 2025.02		70.6