Features
Composite LLM Stats Score aggregating multiple benchmarks
Leaderboard filterable by category (coding, writing, math, etc.)
Model comparison tool with side-by-side scores
Playground for live interaction with hundreds of models
API access to model data and evaluation
Real-time pricing and speed metrics
Open LLM Leaderboard for open-weight models
Arena for community-driven model evaluation (Chat, Coding, Image, Video)
News and blog covering model releases and benchmarks
Search and filter models by organization, context length, and license
Filter by time range (30d, 90d, all)
Dedicated leaderboards for coding, writing, math, research, long context, tool calling, reasoning, image gen, video gen
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
