Features
Reinforcement learning trained chain-of-thought reasoning
89th percentile on Codeforces competitive programming
Top 500 US on AIME math exam (93% accuracy with re-ranking)
PhD-level accuracy on GPQA-diamond (chemistry, physics, biology)
Internal chain of thought hidden from user for safety
Performance scales with test-time compute (more thinking time)
Supports majority vote (consensus) with multiple samples
Supports re-ranking with learned scoring function
Available via API for developers
Vision perception capabilities (MMMU 78.2%)
Local model execution for offline inference
Connect online APIs: OpenAI (ChatGPT), Anthropic (Claude), Google (Gemini), Meta (Llama), Mistral AI, Alibaba (Qwen),
123+ HuggingFace models available
Memory feature (coming soon) for context persistence
Minimalist UI with dark mode
Open source under MIT license on GitHub
Cross-platform desktop app (Mac, Windows, Linux)
Version 0.8.3 with bug fixes and performance improvements
