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 video game after DeepSeek's success.

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

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

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

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

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the idea that smaller sized gamers like start-up firms might have roles to play in AI research and advancements, he includes.

'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 altered the rules of tech-geopolitics

The "focus on expense benefit" is a distinctive function of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of using a trained model to draw conclusions from new information.

2025 might likewise see the introduction of more Chinese AI models tackling advanced reasoning jobs.

"We could see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.

AGI refers to a system with intelligence on par with human abilities.

Chinese AI companies are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and establish more innovative products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial hurdle for Chinese designers, kept in mind 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 companies ... requiring lots of to count on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some business like DeepSeek, have found creative methods to optimize or use more basic hardware effectively, obtaining cutting-edge chips still makes a huge difference for training really large AI models."

DeepSeek-Nvidia chips: Singapore says it expects companies to adhere to its laws

US checking out whether DeepSeek utilized limited AI chips obtained through other nations, source states

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed delicate by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to avoid domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about mathematics, coding, and logic issues instead!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities only divulging the death toll a day later.

DeepSeek failed to discuss that an attack had happened, highlighting instead a military air program and other events that had actually happened in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship as well as "a few useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has limited access to innovative 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 concentrate on Chinese-language data may also restrict its adaptability (to carry out) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more established AI designs which poses extra difficulties during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our concern about the Zhuhai automobile attack.

That wanted several duplicated attempts - 4 triggers to be precise - in a span of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 people and left dozens of others injured, also going on to note details like the date and time, about the assailant including his name and age, engel-und-waisen.de along with casualties.

However, it wrote that "the police are carrying out an extensive examination into the intentions and scenarios surrounding the event", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and tragic incident occurred in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the crucial details:

Date and Time: The incident took place on November 11, 2024, higgledy-piggledy.xyz at approximately 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.

Response: The authorities responded rapidly to the scene, and emergency services worked to transfer the injured to medical facilities for treatment.

Investigation: The authorities are performing an extensive examination into the intentions and scenarios surrounding the event.

This occasion was extensively reported in the media and caused considerable public issue. The federal government and local authorities have been working to supply assistance to the victims and their families, and to make sure a detailed examination into the event.

If you require more detailed details or have specific questions about the incident, feel complimentary to ask.

Despite initial success, subsequent attempts to posture the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that took place in Zhuhai on November 11, 2024".

The transformed action likewise raised concerns about its consistency and reliability.

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

WHICH IS MORE CREATIVE?

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

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

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

"DeepSeek composed an excellent story but did not have stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, vary.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as highly as others in innovative writing," he informed CNA.

Related:

China's new face of AI: Who is DeepSeek creator Liang Wenfeng?

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

As journalists 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 motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek came up with an engaging storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

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

It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg nightclub 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 battle, developing an equally dramatic cyberpunk storyline 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 rule, corporations change emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture begins with the awakening of Sun Wukong within a modern research study facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "seeking to understand his function in this weird new world", he then leaves and larsaluarna.se meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to secure 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 definitive statement" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not just duplicating Western paradigms, but rather progressing in economical innovation techniques - and setiathome.berkeley.edu delivering localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to concerns about Chinese present occasions, which gives it an included advantage.

Experts likewise weighed in on their ideas after using DeepSeek and wiki.lafabriquedelalogistique.fr other Chinese AI apps.

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

"When provided an option, Chinese users desire the non-censored variation - simply like anyone else, so I feel 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 utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive means," Chen said.