ERNIE
Baidu's ERNIE (Wenxin) foundation modelsReference profile
About ERNIE
ERNIE (Wenxin) is Baidu's family of foundation models. ERNIE 5.0 is a unified multimodal model across text, image, video and audio; ERNIE 5.1 followed in May 2026.
Baidu's consumer assistant on these models is Wenxin Assistant (yiyan.baidu.com now leads there), and some models, such as ERNIE-Image, are released with open weights.
Why it matters
ERNIE is Baidu's model family, used across Baidu's search and assistant products.
Updates & reading
ERNIE 5.1 Officially Released! Topping Multiple Leaderboards — A Model That Writes Better and Understands You More
ERNIE 5.1 is derived from ERNIE 5.0, extracting the optimal sub-network architecture from ERNIE 5.0’s multi-dimensional elastic sub-model matrix to effectively inherit the knowledge and capabilities encoded in ERNIE 5.0 while significantly reducing pre-training cost.
ERNIE-5.1-Preview Tops LMArena Text Leaderboard as No.1 Chinese Model!
ERNIE-5.1-Preview builds on the pre-training foundation of ERNIE-5.0 while compressing total parameters to approximately 1/3 and active parameters to approximately 1/2, achieving leading performance at its model scale using only about 6% of the pre-training cost of comparable models.
Introducing ERNIE-Image
From the official blog (ernie.baidu.com), published .
ERNIE 5.0: A 2.4 Trillion-Parameter Unified Multimodal Foundation Model
It is a Unified Multimodal Model trained from scratch to integrate text, images, video, and audio within a single autoregressive framework.
ERNIE-5.0 Tops LMArena Text Leaderboard as No.1 Chinese Model!
ERNIE-5.0 on LMArena is no longer labeled as “Preview” , indicating that the model has completed its preview phase.