Explore a leaderboard of AI models ranked by coding benchmarks like SWE-bench and Codeforces. Discusses challenges and limitations of existing benchmarks.

Explore a bleeding-edge list of AI: models (open weight & proprietary), benchmarks, and applications (chat, image/video/audio, dev tools, and more).

Compare AMIodel factuality with the SimpleQA leaderboard. Includes scores for AIME'25 (Math), Chatbot Arena, and ArenaHard benchmarks.

Learn how to choose the right LLM quantization for your local setup. This guide explains the importance of model size, bits, RAM, and GPU offloading for faster performance.