Features
Multi-model blind peer review (3 models from different providers)
Pre-analysis: identifies hidden assumptions and failure modes
Adversarial refinement with iterative improvement loops
Anti-sycophancy detection with over-compliance risk scoring
Convergence analysis to flag correlated hallucinations
Claim verification against live web sources (verified/unverified/contradicted)
Devil's advocate final critique (survives/weakened/refuted)
MCP integration (use inside Claude, ChatGPT, or any AI)
Web search retrieval for current information
File and PDF upload (paid plans)
Session history (90 days on Reasoner, unlimited on Architect+)
Concurrent sessions (Collective plan up to 10)
Credit-based usage with no subscription option
Priority queue on paid plans
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
