ERNIE 5.0 Thinking Preview

ERNIE 5.0 Thinking Preview

Baidullm

Grande modelo de linguagem (llm) desenvolvido pela Baidu — Intelligence Index 29/100 no Artificial Analysis; acesso gratuito.

API Available

Specifications

Context Window

Input Price/1M

Output Price/1M

Parameters

00

Benchmarks

ERNIE 5.0 Thinking Preview results on the main AI model evaluation benchmarks. Higher scores indicate better performance.

Agentic

BenchmarkScoreMaximumMethodology
Terminal-Bench Hard25.0100.0

Coding

BenchmarkScoreMaximumMethodology
LiveCodeBench81.0100.0Artificial Analysis official API
SciCode38.0100.0
AA Coding Index29.2100.0Artificial Analysis official API

Knowledge

BenchmarkScoreMaximumMethodology
MMLU-Pro83.0100.0

Long Context

BenchmarkScoreMaximumMethodology
AA-LCR7.0100.0

Math

BenchmarkScoreMaximumMethodology
AIME 202585.0100.0Artificial Analysis official API
AA Math Index85.0100.0Artificial Analysis official API

overall

BenchmarkScoreMaximumMethodology
AA Intelligence Index29.1100.0Artificial Analysis official API

Reasoning

BenchmarkScoreMaximumMethodology
MMLU Pro83.0100.0Artificial Analysis official API
GPQA Diamond78.0100.0Artificial Analysis official API
IFBench41.0100.0
HLE13.0100.0

Tool Use

BenchmarkScoreMaximumMethodology
Tau²-Bench84.0100.0

Information

Release date
November 13, 2025
Tool Calling
❌ Not supported
Vision
❌ Not supported
Audio
❌ Not supported

Full Analysis: ERNIE 5.0 Thinking Preview

What is ERNIE 5.0 Thinking Preview?

ERNIE 5.0 Thinking Preview is an AI model developed by Baidu, classified as a llm model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Baidu's cloud API.

Pricing & Costs in 2026

ERNIE 5.0 Thinking Preview does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check Baidu's official website for up-to-date availability and pricing.

Benchmarks & Performance

ERNIE 5.0 Thinking Preview was evaluated on 14 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show solid performance across available evaluations.

It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.

Recommended Use Cases

ERNIE 5.0 Thinking Preview is suitable for a wide range of AI applications: text generation, summarization, translation, and general assistance.

Comparison with Alternatives

In the 2026 AI model ecosystem, ERNIE 5.0 Thinking Preview competes directly with similarly capable models. Baidu competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.

For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.

Frequently Asked Questions

What is ERNIE 5.0 Thinking Preview?

ERNIE 5.0 Thinking Preview is an AI model developed by Baidu. It is a llm model.

How much does ERNIE 5.0 Thinking Preview cost?

ERNIE 5.0 Thinking Preview does not have public per-token pricing available at this time. Check Baidu's official website for up-to-date information.

How does ERNIE 5.0 Thinking Preview compare with other models?

In available benchmarks, ERNIE 5.0 Thinking Preview scored: Terminal-Bench Hard: 25/100, LiveCodeBench: 81/100, SciCode: 38/100. See the full table above for a detailed comparison.

Is ERNIE 5.0 Thinking Preview open source?

No, ERNIE 5.0 Thinking Preview is a proprietary model from Baidu. It is available via cloud API. For open source alternatives, check our open source model ranking.

What is ERNIE 5.0 Thinking Preview best for?

ERNIE 5.0 Thinking Preview excels at general-purpose language tasks.

Last updated: June 01, 2026 View methodology →