highpriceddatinguk

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 startup 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 lags CHINA'S AI BOOM?

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

China views AI as being "tactically essential" and its foray into the field has 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 revealed guarantees of real-world organization applications, Chen told CNA.

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

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

Commentary: DeepSeek - how a Chinese AI company just altered the rules of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the expenses of utilizing a trained design to draw conclusions from new information.

2025 might also see the development of more Chinese AI models tackling innovative reasoning tasks.

"We could see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with scientific research study," Chen added.

AGI refers to a system with intelligence on par with .

Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods 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 an essential 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) restrict the ability of Chinese tech business ... forcing many to depend on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some companies like DeepSeek, have discovered innovative methods to enhance or use more basic hardware efficiently, obtaining innovative chips still makes a huge difference for training large AI designs."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, source says

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, topics considered delicate 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 tell you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed 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 mathematics, coding, and logic problems rather!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "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 greatly censored on Chinese social networks - with authorities only revealing the death toll a day later.

DeepSeek failed to discuss that an attack had occurred, highlighting instead a military air program and other occasions that had actually occurred in the city like singles' day shopping sales as well as sports and cultural activities.

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

"DeepSeek counts on a mix of older graphics processing units and has restricted access to advanced hardware which can impact how rapidly and thoroughly the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data may also limit its flexibility (to carry out) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more established AI models which postures additional difficulties during real-world implementation."

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

That wanted several duplicated attempts - four prompts to be accurate - in a span of around 20 minutes.

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

However, it composed that "the authorities are conducting a comprehensive investigation into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and awful event occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, wiki.asexuality.org leading to a substantial number of casualties. Here are the essential details:

Date and Time: The occurrence took place 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 old), was captured by the cops.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to carry the injured to hospitals for treatment.

Investigation: The police are carrying out a comprehensive examination into the intentions and circumstances surrounding the event.

This event was widely reported in the media and caused considerable public issue. The federal government and local authorities have actually been working to offer assistance to the victims and their families, and to ensure a detailed examination into the occurrence.

If you require more detailed details or have specific questions about the occurrence, feel totally free to ask.

Despite preliminary success, subsequent efforts to posture the same concern to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".

The altered action also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been widely released in global report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that builds slowly from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more considerable twist".

"DeepSeek wrote a great story however did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, 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 creative writing," he told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide 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 movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

It included intricate 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 also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed an excellent battle, creating a similarly dramatic cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary 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 misconceptions."

Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that seemed more fit for an animation movie.

"The movie begins with the awakening of Sun Wukong within a high-tech research study center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "seeking to understand his purpose in this unusual new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem 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 "challenging to make a definitive statement" about which bot was best, including that each showed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, however rather evolving in affordable development approaches - and providing localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed its imaginative flair that made for a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to questions about Chinese existing events, which provides it an added benefit.

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

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

"When provided a choice, Chinese users desire the non-censored variation - similar to anybody 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, especially for Chinese users.

"Ninety percent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive means," Chen said.