ERNIE-4.5-VL-424B-A47B-Base

Name: ERNIE-4.5-VL-424B-A47B-Base
Author: Baidu

Multimodal modelERNIE-4.5

Release date: 2025-06-30Updated: 2025-06-30Views: 906

Live demoGitHubHugging Face Compare

Parameters

424B

Context length

128K

Multilingual

Supported

Reasoning ability

4/5

ERNIE-4.5-VL-424B-A47B-Base is an AI model published by Baidu, released on 2025-06-30, for Multimodal model, with 424B parameters, and 128K context length, requiring about 717.95 GB storage, with a 76.80 score on GPQA Diamond.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

ERNIE-4.5-VL-424B-A47B-Base

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

32K tokens

Model type

Multimodal model

Modality (in / out)

Text, Image → Text, Image

Release date

2025-06-30

Model file size

717.95 GB

MoE architecture

Yes

Total params / Active params

424B / 47B

Knowledge cutoff

No data

ERNIE-4.5-VL-424B-A47B-Base

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- Commercial use permitted

GitHub repo

N/A

Hugging Face

huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Bas…

Live demo

yiyan.baidu.com

ERNIE-4.5-VL-424B-A47B-Base

Official resources

Paper

N/A

DataLearnerAI blog

N/A

ERNIE-4.5-VL-424B-A47B-Base

API details

API speed

2/5

No public API pricing yet.

ERNIE-4.5-VL-424B-A47B-Base

Benchmark Results

ERNIE-4.5-VL-424B-A47B-Base currently shows benchmark results led by GPQA Diamond (267 / 462, score 76.80), MMMU (45 / 74, score 70), LiveCodeBench (189 / 250, score 38.80). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.