List your company

Question Answering on TeleQnA Public Subset

86.6AccuracyLlama 3.1 405B
53.94462.42270.979.378Aug 20, 2024

Evaluation results

MethodLinks
Llama 3.1 405BContext + TAE=true, Options=true2024.0886.6
Claude 3.5 SonnetContext + TAE=true, Options=true2024.0884.7
GPT-4o-miniContext + TAE=true, Options=true2024.0883.3
Phi-2Context + TAE=true, Options=true2024.0880.3
Llama 3.1 405BContext + TAE=true, Options=false2024.0872.7
Claude 3.5 SonnetContext + TAE=false, Options=true2024.0871.6
Llama 3.1 405BContext + TAE=false, Options=true2024.0869.7
GPT-4o-miniContext + TAE=true, Options=false2024.0868.9
Claude 3.5 SonnetContext + TAE=true, Options=false2024.0868.6
GPT-4o-miniContext + TAE=false, Options=true2024.0865.3
Falcon-7BContext + TAE=true, Options=false2024.0860.1
Phi-2Context + TAE=false, Options=true2024.0855.2