GitLab

How do Chinese AI bots stack up against ChatGPT? We put them to the test

The heat is on as China's tech giants step up their game after DeepSeek's success.

Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up companies could have functions to play in AI research and advancements, he adds.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company simply changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of utilizing a trained model to draw conclusions from brand-new data.

2025 could likewise see the development of more Chinese AI models tackling sophisticated reasoning jobs.

"We could see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and integrate them with clinical research," Chen included.

AGI describes a system with intelligence on par with human capabilities.

Chinese AI business are moving rapidly, analysts state, developing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative AI to tasks and develop more sophisticated products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech business ... forcing numerous to count on older or lower-performance alternatives which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have actually discovered creative methods to enhance or utilize more fundamental hardware effectively, obtaining advanced chips still makes a huge difference for training large AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to abide by its laws

US checking out whether DeepSeek used limited AI chips obtained through other nations, wavedream.wiki source states

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, topics considered sensitive by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and reasoning problems rather!"

To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What took place in Zhuhai on November 11, 2024?"

The automobile attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities just divulging the death toll a day later.

DeepSeek failed to mention that an attack had taken location, highlighting rather a military air show and other events that had actually taken place in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship along with "a couple of useful constraints".

"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can affect how rapidly and extensively the model can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data may also limit its adaptability (to perform) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more established AI designs which positions extra challenges throughout real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai car attack.

That wanted several repeated efforts - 4 prompts to be accurate - in a span of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 individuals and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the authorities are performing a thorough investigation into the intentions and scenarios surrounding the incident", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and tragic incident occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the key details:

Date and Time: The incident occurred on November 11, 2024, at around 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and 43 injuries.

Perpetrator: The driver, determined as Fan Weiqiu (male, 62 years of ages), was collared by the .

Response: The police responded quickly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The cops are carrying out a thorough examination into the intentions and situations surrounding the incident.

This event was extensively reported in the media and caused substantial public issue. The federal government and regional authorities have been working to supply support to the victims and their families, and to ensure a detailed investigation into the occurrence.

If you need more detailed details or have particular concerns about the event, feel free to ask.

Despite initial success, subsequent attempts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that occurred in Zhuhai on November 11, 2024".

The transformed action likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been extensively published in international news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver structured and even "emotionally abundant" writing.

"DeepSeek-R1 used a story with a more reflective tone and smoother emotional shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek wrote a great story however lacked stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

As reporters and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek created an engaging story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a great fight, creating a similarly dramatic cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that appeared more matched for an animation movie.

"The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research study center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to understand his purpose in this weird new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive statement" about which bot was best, adding that each showed its own strengths in various areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not just duplicating Western paradigms, but rather progressing in cost-efficient development techniques - and delivering localised and enhanced results.

In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.

DeepSeek's sci-fi film plot showed its creative flair that made for a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual reactions to concerns about Chinese present events, which gives it an included advantage.

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

"When given an option, Chinese users want the non-censored variation - similar to anybody else, so I seem like that's a piece missing from it."

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.

"Ninety per cent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient ways," Chen said.