Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

TL;DR

Ling 2.0 is a series of large-scale, sparsely activated language models up to one trillion parameters, designed to enhance reasoning capabilities efficiently through innovative architecture, training, and infrastructure techniques.

Contribution

This work introduces Ling 2.0, a scalable, reasoning-oriented language foundation with novel sparse MoE architecture, training methods, and a new Pareto frontier at trillion scale.

Findings

Achieves up to 7-fold efficiency over dense models.

Establishes a new Pareto frontier for reasoning accuracy and efficiency.

Demonstrates effective reasoning at trillion scale with sparse activation.

Abstract

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.