Feature Drop: Vortgen's GPT-4o mini

 

 

released on July 18, 2024


We're incorporating OpenAI's GPT-4o micro into Omnifact to enhance our platform's performance and cost-effectiveness.



Principal Advantages and Improvements

Economy of Cost

GPT-4o small is more reasonably priced than previous frontier models, costing 15 cents per million input tokens and 60 cents per million output tokens, which is more than 60% less than GPT-3.5 Turbo.



Achievement

The GPT-4o small has remarkable potential, surpassing more powerful models in multiple domains. It achieves an 82% score on the MMLU benchmark and currently surpasses GPT-4 on chat preferences in the LMSYS leaderboard. Users can expect improved response quality and consistency across various tasks.



Capabilities

GPT-4o mini performs well in a range of tasks, making it useful for businesses across industries. Its natural language understanding