lm-sys / FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Repository from Github https://github.comlm-sys/FastChatRepository from Github https://github.comlm-sys/FastChat

Delayed Response

DominicTWHV opened this issue · comments

When comparing a reasoning model with a non-reasoning model, disable streaming, and post both responses to the user at the same time after both of the models are done to prevent the user from using model response times (ie longer response time = some sort of reasoning model) to bias voting.