ERNIE 5.0 Thinking Preview

Name: 文心一言 ERNIE 5.0 Thinking Preview
Author: 百度

Reasoning modelERNIE 5.0

文心一言 ERNIE 5.0 Thinking Preview

Release date: 2025-11Updated: 2026-04-06 11:21:59.641236

Live demoGitHubHugging FaceCompare

Parameters

2.4T

Context length

128K

Chinese support

Supported

Reasoning ability

文心一言 ERNIE 5.0 Thinking Preview is an AI model published by 百度, released on 2025-11, for Reasoning model, with 2.4T parameters, and 128K context length, under the 不开源 license, with a 51.00 score on Claw Bench.

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

ERNIE 5.0 Thinking Preview

Model basics

Reasoning traces

Supported

Thinking modes

Thinking Mode (Default)Standard Mode

Context length

128K tokens

Max output length

8K tokens

Model type

Reasoning model

Modality (in / out)

No data

Release date

2025-11

Model file size

No data

MoE architecture

Yes

Total params / Active params

2.4T / N/A

Knowledge cutoff

No data

ERNIE 5.0 Thinking Preview

Open source & experience

Code license

不开源

Weights license

不开源

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

https://ernie.baidu.com/

ERNIE 5.0 Thinking Preview

Official resources

Paper

ERNIE 5.0: A 2.4 Trillion-Parameter Unified Multimodal Foundation Model

DataLearnerAI blog

No blog post yet

ERNIE 5.0 Thinking Preview

API details

API speed

3/5

No public API pricing yet.

ERNIE 5.0 Thinking Preview

Benchmark Results

ERNIE 5.0 Thinking Preview currently shows benchmark results led by Claw Bench (29 / 29, score 51). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.