Features
Page Context understanding (headings, sections, text)
Snap Screen visual intelligence for screenshots, charts, tables
Summarize any page or PDF in bullet points
Explain code blocks and identify issues
Live web research with citations
PDF conversation (open PDFs and chat)
Model switching (Gemini, Claude, ChatGPT, Grok, DeepSeek)
Conversation continuity across tabs
Zero data logging for privacy
Requires user-provided API key
Chrome extension only (no other browsers)
Agentic integrations coming soon (Gmail, Asana, GitHub, Notion)
Official LLM leaderboard and ranking
Battle Mode for side-by-side model comparison
Agent Mode for real-world agent evaluation
Multimodal Max for multimodal model testing
Code Arena with web development challenge categories
BullshitBench for nonsense detection evaluation
File upload for third-party AI processing
Public conversation sharing for community research
Leaderboard dataset publicly available
Monthly arena updates across product and research
Search functionality for models and conversations
Community voting on model responses
