palm-2· Google Arena Human Preference 55K
Lol
- User
Lol
- Assistant
I'm glad to see you're in a good mood.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- gpt-4-1106-previewCompare side by side →
- gemini-pro-dev-apiCompare side by side →
- claude-2.1Compare side by side →
- vicuna-33bCompare side by side →
- mpt-7b-chatCompare side by side →
- fastchat-t5-3bCompare side by side →
- alpaca-13bCompare side by side →
- gpt-4-1106-previewCompare side by side →
- gpt-3.5-turbo-1106Compare side by side →