bytes-the-dust

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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

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

China views AI as being "tactically essential" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated 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 wiki.whenparked.com showed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller sized gamers like start-up companies might have functions to play in AI research study 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 business simply altered the rules of tech-geopolitics

The "emphasis on cost benefit" is a distinctive function of Chinese AI, Chen states, with lower training and inference costs - the expenses of utilizing a trained design to draw conclusions from new information.

2025 might also see the emergence of more Chinese AI designs dealing with innovative reasoning tasks.

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

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

Chinese AI business are moving rapidly, analysts state, building on to come up with their own innovative and cost-efficient ways to apply generative AI to tasks and develop more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains an essential 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) restrict the ability of Chinese tech companies ... requiring many to depend on older or lower-performance options which can slow training and reduce model abilities," she said.

"While some companies like DeepSeek, have actually found innovative methods to optimize 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 adhere to its laws

US checking out whether DeepSeek used 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 deemed sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to guide clear of 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 issues rather!"

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

The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only divulging the death toll a day later.

DeepSeek failed to mention that an attack had occurred, highlighting rather a military air show and other occasions that had occurred in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it may be a mix of factors at play, bytes-the-dust.com such as censorship as well as "a few useful constraints".

"DeepSeek depends on a mix of older graphics processing systems and has restricted access to innovative hardware which can affect how quickly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more recognized AI designs which presents additional obstacles during real-world release."

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

That wanted multiple duplicated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately relayed details about the attack which killed 35 people and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the cops are performing a thorough investigation into the intentions and circumstances surrounding the event", details which is now outdated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and awful event occurred in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

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

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

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

Perpetrator: The chauffeur, identified as Fan Weiqiu (male, 62 years old), was apprehended by the cops.

Response: The authorities responded quickly to the scene, and emergency situation services worked to carry the injured to hospitals for treatment.

Investigation: The authorities are carrying out an extensive examination into the motives and situations surrounding the incident.

This occasion was widely reported in the media and triggered considerable public issue. The government and local authorities have actually been working to offer assistance to the victims and their households, and to ensure a detailed investigation into the event.

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

Despite preliminary success, subsequent attempts to pose the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that took place in Zhuhai on November 11, 2024".

The modified reaction also raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been widely published in global news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to deliver structured and even "mentally rich" writing.

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

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

"DeepSeek composed a great story however did not have tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he informed 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 shocks international 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 fundamental sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

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

It included fancy 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 remarkably reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up an excellent battle, coming up with an equally significant cyberpunk storyline which likewise 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 obstacle - providing a storyline that appeared more suited for an animation movie.

"The motion picture starts with the awakening of Sun Wukong within a high-tech research 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 odd new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a conclusive statement" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not just reproducing Western paradigms, but rather developing in economical innovation techniques - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot showed its creative flair that made for a more interesting and imaginative story 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 concerns about Chinese existing events, which provides it an included benefit.

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

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

"When offered an option, Chinese users desire the non-censored version - much like anyone 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, especially for Chinese users.

"Ninety per cent of individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient methods," Chen said.