Skip to content
AIMarketCap

ERNIE 5.0

Model

2.4-trillion-parameter unified native multimodal foundation model spanning text, image, video and audio.

Released
Feb 6, 2026
Context window
—
Modality
textimagevideoaudio
Open source
—
API available
—
Releases
1

Releases

1
Feb 6, 2026ERNIE 5.0 officially releasedERNIE 5.0

Baidu released a 2.4T-parameter unified model trained jointly across text, image, video and audio.