inclusionAI/Ling-1T

Ling-1T is a 1 trillion total parameter, 50 billion active parameter model from inclusionAI, built on the Ling 2.0 architecture. Pre-trained on over 20 trillion reasoning-dense tokens, it supports up to 128K context length and utilizes an evolutionary chain-of-thought (Evo-CoT) process. This model excels in efficient complex reasoning, outperforming leading models on benchmarks like AIME 25, and demonstrates strong capabilities in visual aesthetics and front-end code generation.