Baidu’s ERNIE 5 AI Model Rises Up the Rankings—A Math Wiz That Beats OpenAI’s GPT 5.1

Chinese tech giant Baidu just updated it’s state-of-the-art AI model—and it’s apparently pretty good.

The company’s ERNIE-5.0-0110 scored 1,460 points on LMArena’s Text leaderboard, landing at #8 globally and becoming the sole Chinese model to crack the platform’s top 10. It ranked ahead of OpenAI’s GPT-5.1-High and Google’s Gemini-2.5-Pro. ERNIE v4.0 was released in 2023.

ERNIE 5.0 also claimed the #2 spot globally for mathematical reasoning, trailing only the unreleased GPT-5.2-High. For a Chinese model to outperform nearly every publicly available Western system on complex logical tasks marks a significant shift in the AI capability gap—or rather, its closing.

Baidu’s announcement on X emphasized that ERNIE 5.0 has officially exited its preview phase. The model also demonstrated competitive performance in creative writing, instruction following, and coding—ranking in the top 10 across multiple occupational categories including science, business and finance, and healthcare.

The technical architecture behind these results follows China’s focus on efficiency rather than raw power. ERNIE 5.0 uses a roughly 2-trillion-parameter Mixture-of-Experts architecture, activating only a small fraction of experts (just 3% to be more accurate) per inference.

Like other sparse frontier models, this design reduces per-query compute compared with dense systems, though it introduces additional engineering complexity. Baidu also said that ERNIE 5.0 was trained natively across text, images, audio, and video, rather than retrofitting multimodal modules onto a language-only core. The company said this makes Ernie a natively “omni-modal” AI model.

The comeback is notable given how far Baidu had fallen. In November, ERNIE 5.0’s preview version had dropped to 24th place on LMArena. The domestic AI market had been dominated by nimbler competitors: ByteDance’s Doubao commanded 101 million monthly active users while DeepSeek’s cost-efficient models triggered a price war that forced Baidu to abandon its paid subscription model entirely in last April.

But the consumer struggles haven’t slowed Baidu’s enterprise momentum. ERNIE now powers smart city command centers across China, serves all systemically important Chinese banks, and processes 16.5 billion API calls daily. This B2B stronghold has insulated Baidu from the cutthroat consumer competition while funding continued model development.

Beyond the pure raw power of the LLM, the UI for the ERNIE chatbot is pretty user-friendly and packed with pre-customized features that help users get more tailored results based on their needs. For example, instead of making users deal with complex prompts for different tasks, the chatbot offers separate sections for writing, reading, image editing, and general use. It’s the same core model, but the variations in the system prompt and tweaks make each task easier to accomplish.

Interestingly enough, the most recent version does not come with web search enabled, so it’s purely offline. However, users can switch to the previous Ernie 4.5 and get updated information with web search enabled.

Reactions have been mixed, with some users still awaiting a more detailed breakdown of the model’s performance and benchmarks, which the company promised to release soon. Also, it is important to consider that while ERNIE 5.0 matches GPT-5 and Gemini 2.5 on specific benchmarks, many Western labs have already moved to GPT-5.2 or Gemini 3, making this more of a catch-up than a leap ahead.

Users can test the model for free at ernie.baidu.com.