DataLearner logo
ER

ERNIE 5.0

Multimodal modelERNIE 5.0

Baidu ERNIE 5.0

Release date: 2025-11-13Updated: 2026-07-17 23:18:45.2671,263
Live demoGitHubHugging FaceCompare
Parameters
2.4T
Context length
128K
Chinese support
Supported
Reasoning ability

ERNIE 5.0 is a multimodal model from Baidu, released on 2025-11-13. It accepts text, image, audio, and video input and returns text, image, audio, and video output. The cataloged parameter count is 2.4T. The recorded context window is 128K, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

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

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
128K tokens
Max output length
64K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Text, Image, Audio, Video
Release date
2025-11-13
Model file size
No data
MoE architecture
Yes
Total params / Active params
2.4T / N/A
Knowledge cutoff
No data
ERNIE 5.0

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
https://ernie.baidu.com/
ERNIE 5.0

Official resources

Paper
Paper
DataLearnerAI blog
No blog post yet
ERNIE 5.0

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
TextContext <= 32000¥6.00/ 1M¥24.00/ 1M
TextContext > 32000, Context <= 128000¥10.00/ 1M¥40.00/ 1M
ERNIE 5.0

Benchmark Results

ERNIE 5.0 currently shows benchmark results led by SimpleQA (5 / 47, score 74.01), GPQA Diamond (46 / 188, score 86.36), LiveCodeBench (37 / 123, score 76.21). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
86.36
46 / 188
MMLU Pro
Thinking Mode
83.80
42 / 132
HLE
Thinking Mode
25.81
99 / 173

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Thinking Mode
74.01
5 / 47

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
76.21
37 / 123

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
89.06
40 / 107

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
Thinking Mode
78.79
18 / 43
View benchmark analysisCompare with other models

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

ERNIE 5.0

Publisher

Baidu ERNIE 5.0

Model Overview

ERNIE 5.0 is a multimodal model from Baidu, released on 2025-11-13.

It accepts text, image, audio, and video input and produces text, image, audio, and video output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 2.4T. The recorded context window is 128K, and the recorded maximum output is 64K.

The model weights are proprietary and are not published for download. The page records 4 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment. The evaluation section contains 7 cataloged benchmark results with their recorded modes and scores. The page links 2 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

ERNIE 5.0

FAQ

What is ERNIE 5.0?

ERNIE 5.0 is a multimodal model from Baidu, released on 2025-11-13. It accepts text, image, audio, and video input and returns text, image, audio, and video output. The cataloged parameter count is 2.4T. The recorded context window is 128K, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model and Multilingual. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does ERNIE 5.0 support?

The current model record lists text, image, audio, and video as input and text, image, audio, and video as output.

What are the main recorded specifications for ERNIE 5.0?

The cataloged parameter count is 2.4T. The recorded context window is 128K, and the recorded maximum output is 64K. Fields without a source-backed value remain undisclosed.

Does ERNIE 5.0 have API pricing?

The page records 4 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for ERNIE 5.0?

The evaluation section contains 7 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is ERNIE 5.0 open source?

The model weights are proprietary and are not published for download. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code