Skip to content

Baidu Proprietary Released Jan 22, 2026 Updated

ERNIE 5.0

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #104 / 419

    365 / 1,000

    ToolsGuide Score· votes 406, tests 330

  • Price per 1M tokens

    No listed price

Summary

ERNIE 5.0 is Baidu's model, released Jan 22, 2026. It's ranked in 1 category and does best at text: #104 of 419, with a ToolsGuide Score of 365 against a median of 252.

It has published results on 5 tests.

Specifications

Creator
Baidu
Licence
Proprietary
Released
Jan 22, 2026
Context window
–
Input price
–
Output price
–
Tests reported
5
Settings ranked
ERNIE 5.0 (0110)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where ERNIE 5.0 sits among the top 20 in each category.

Text

#104 of 419 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

ERNIE 5.0 (0110) · hover a bar for its rank

Test results

Every test ERNIE 5.0 has a published result on, out of 100%, with its rank among the models that took it.

  • GPQA

    #74 / 265

    Graduate-level science questions written to be hard to look up.

    85.0%

    Self-reported

  • MMLU-Pro

    #9 / 142

    Broad knowledge and reasoning across 14 subjects, ten answer choices each.

    87.0%

    Self-reported

  • AIME 2025

    #59 / 124

    Competition maths problems from the 2025 American Invitational Mathematics Exam.

    87.0%

    Self-reported

  • Humanity's Last Exam

    #43 / 115

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    39.0%

    Self-reported · In the text score· In the vision score

  • SimpleQA

    #5 / 47

    SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326 short, fact-seeking questions that are adversarially collected and designed to have single, indisputable answers. Questions cover diverse topics from science and technology to entertainment, and the benchmark also measures model calibration by evaluating whether models know what they know.

    75.0%

    Self-reported