
GLM-5.2 tops the open-weights leaderboard with a 51 Intelligence Index, 1M context, and MIT license. Benchmarks vs DeepSeek V4 Pro and Kimi K2.6.

Compare Gemini 3.5 Flash, Claude Sonnet 4.6, and GPT-4.1 Mini on speed, cost, quality, and tool calling. Benchmarks and code examples.