5 articles
Baidu unveils ERNIE 5.0, a next-generation omni-modal AI model that processes text, images, audio, and video through a single unified framework, featuring 2.4 trillion parameters with under 3% activation per inference for efficient multimodal reasoning.
Baidu's ERNIE 5.0 achieves impressive benchmark scores with its massive 2.4 trillion-parameter design, but real-world testing exposes critical problems with following instructions and controlling tool usage.
ERNIE 5.0 is being marketed as a massive AI model with over 2.4 trillion parameters using a super-sparse MoE architecture. While benchmark charts show impressive text performance against top competitors, early hands-on testing reveals serious instruction-following problems.
Baidu has announced ERNIE 5.0, a new omni-modal AI model showing impressive benchmark results across text, vision, audio, and image generation.
ERNIE 5.0 Preview has grabbed the No. 2 spot on the LMArena Text Arena leaderboard with a score of 1432, marking a significant achievement for Baidu's next-generation AI model.
We use cookies to improve your experience on our site and to show you relevant advertising. To find our more, read our privacy policy and cookie policy
Eseandre Mordi
Usman Salis
Peter Smith
Saad Ullah
