Baidu has officially released ERNIE LLM 5.1, based on multi-dimensional elastic pretraining technology, achieving leading baseline performance with only about 6% of the pretraining cost of same-scale industry models, and topping LMAarena's search ranking #1 in China and #4 globally.
The core of this technology is the Once-for-All elastic training framework. Through three dimensions — elastic depth (randomly skipping Transformer layers), elastic width (dynamically adjusting the MoE expert pool), and elastic sparsity (variable Top-k routing) — the framework achieves the ability to generate models of various sizes from a single pretraining run, compressing total parameters to about 1/3 of ERNIE 5.0, and activated parameters to about 1/2.
The post-training stage adopts a decoupled fully-asynchronous RL architecture, with the control planes of training, inference, reward, and agent loop subsystems fully decoupled, combined with an FP8 low-precision operator library and OPD multi-stage training pipeline, effectively solving the seesaw-effect problem, and achieving balanced improvement across Agent, reasoning, and creative capabilities. On the AIME26 math competition evaluation, ERNIE 5.1 scored 99.6, second only to Gemini 3.1 Pro.
The significance of ERNIE 5.1 goes beyond a single training efficiency breakthrough — it lies in the elastic training paradigm itself: using fewer resources to build more models is becoming the new dividing line in LLM competition.