GPT-4 Tops Chatbot Rankings

Loading data from Talking to Chatbots Dataset reddgr/talking-to-chatbots-chats

😎

the chart shows the number of different types of the different types of the different types of the different types of
🤖 Here’s an ALT text for the image:

A table titled “LLM Battle: HumbleAI Chatbot” showing a ranking of chatbots. The columns list ‘Chatbot’, ‘Rank (SCBN)’, ‘Specificity’, ‘Coherence’, ‘Brevity’, ‘Novelty’, and ‘Link’. GPT-4 is ranked as ‘Winner’ with the highest scores in all categories. Gemini is ‘Runner-up’, and Mixtral, Nous, Mistral7B are ‘Contender’. OpenChat and Llama2 have the lowest scores. Each category, except ‘Rank’, is rated with 1 to 5 icons that look like chat bubbles, with GPT-4 receiving the maximum of 5 in each. Each row ends with a ‘View Chat’ link.
[Alt text by ALT Text Artist GPT]

Hugging Face Dataset Metrics

All the conversation prompts, responses, and metrics are available to download and explore on Hugging Face dataset reddgr/talking-to-chatbots-chats: