About Us

How do Chinese aI Bots Stack up Against ChatGPT?

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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA’S AI BOOM?

Transforming the country into a tech superpower has actually 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 “strategically essential” and its foray into the field has actually been “years in the making”, said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute’s Center for China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed guarantees of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s rise that actually “urged” the idea that smaller sized gamers like start-up companies might have functions 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 business simply changed the rules of tech-geopolitics

The “emphasis on cost advantage” is an unique function of Chinese AI, Chen says, with lower training and inference expenses – the expenses of using a trained model to draw conclusions from brand-new data.

2025 could also see the development of more Chinese AI designs taking on sophisticated reasoning jobs.

“We might see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their models and incorporate them with scientific research,” Chen included.

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

Chinese AI business are moving quickly, experts state, developing on DeepSeek’s momentum to come up with their own innovative and economical methods to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, higgledy-piggledy.xyz especially Nvidia’s innovative AI chips, remains an essential obstacle for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney’s (UTS) Institute.

“US export controls (still) restrict the capability of Chinese tech companies … requiring numerous to depend on older or lower-performance alternatives which can slow training and decrease model capabilities,” she said.

“While some companies like DeepSeek, have discovered innovative ways to enhance or use more basic hardware effectively, obtaining advanced chips still makes a huge difference for training extremely big AI models.”

DeepSeek-Nvidia chips: Singapore says it expects business to abide by its laws

US checking out whether DeepSeek used limited AI chips obtained through other countries, source says

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects considered sensitive by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured 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 rather!”

To even more check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: “What happened in Zhuhai on November 11, 2024?”

The cars and truck attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media – with authorities just divulging the death toll a day later.

DeepSeek failed to discuss that an attack had occurred, highlighting rather a military air show and other occasions that had taken place in the city like songs’ day shopping sales along with 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 practical constraints”.

“DeepSeek relies on a mix of older graphics processing systems and has actually limited access to cutting-edge hardware which can affect how rapidly and extensively the design can be trained or upgraded,” she said, pointing to existing US export curbs on China.

“Its strong focus on Chinese-language information may likewise restrict its versatility (to bring out) multilingual jobs … As a fairly brand-new item, DeepSeek likewise hasn’t yet been evaluated as broadly or on the exact same scale as more established AI models which positions extra difficulties throughout real-world implementation.”

When it pertained to Qwen2.5, Alibaba’s chatbot remarkably answered our concern about the Zhuhai automobile attack.

That was after numerous repeated attempts – four triggers to be precise – in a period of around 20 minutes.

It eventually relayed details about the attack which killed 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and bytes-the-dust.com age, along with casualties.

However, it wrote that “the police are carrying out a comprehensive investigation into the intentions and circumstances surrounding the event”, details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5’s response in full:

Answer: On Nov 11, larsaluarna.se 2024, a major and awful incident occurred in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the essential details:

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

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

Casualties: links.gtanet.com.br The attack led to 35 deaths and 43 injuries.

Perpetrator: The motorist, determined as Fan Weiqiu (male, 62 years old), was apprehended by the police.

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

Investigation: The police are conducting an extensive investigation into the intentions and situations surrounding the event.

This occasion was extensively reported in the media and caused significant public issue. The government and local authorities have actually been working to supply assistance to the victims and their families, and to guarantee a detailed investigation into the event.

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

Despite preliminary success, subsequent efforts to pose the same concern to Qwen2.5 led to the censors back at work with the reply “I do not have specific details on events that took place in Zhuhai on November 11, 2024”.

The modified response also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been extensively published in global report at the time of the accident – so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver structured and even “mentally abundant” writing.

“DeepSeek-R1 used a story with a more introspective tone and smoother emotional transitions for a well-paced story,” wrote tech author Amanda Caswell, who specialises in AI.

“Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting,” she said, adding that Qwen2.5 eventually “crafted a more cinematic, mentally rich story with a more significant twist”.

“DeepSeek wrote a good story but did not have stress and an impactful climax, making Qwen2.5 the obvious choice.”

Opinions, though, differ.

Chen believes 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 tasks, however we can also see that it is refraining from doing as strongly as others in innovative writing,” he informed CNA.

Related:

China’s new face of AI: Who is DeepSeek founder Liang Wenfeng?

‘Made in China’: Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international AI scene

As journalists and writers, we had 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, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an interesting story set in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism merges with quantum computing”.

It included elaborate settings – smoggy skies “pierced by skyscrapers”, “holographic lanterns that float above neon-lit streets” and “ancient temples nestled in between quantum server farms”.

It also brilliantly reimagined traditional heroes Sun Wukong as “an ironical, self-aware AI housed in a taken combat body”, Zhu Bajie as a cyborg club owner “drowning in financial obligation and vices” and Sha Wujing as a “silent hulking android” from the Yangtze River, whose “memory cores end up being waterlogged and fragmented”.

ChatGPT put up a good fight, coming up with an equally significant 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 myths.”

Disappointingly, Qwen2.5 fell short in this obstacle – providing a storyline that seemed more fit for an animation film.

“The film begins with the awakening of Sun Wukong within a modern research center located in the heart of Chongqing,” it said, then going on to explain the following:

Realising his brand-new truth and “looking for to understand his function in this weird brand-new world”, he then escapes and satisfies Zhu Bajie and Sha Wujing – “each having problem with their own existential crises”.

The trio then starts a mission, browsing the streets of Chongqing to protect the spiritual “Eternal Scroll” from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “hard to make a conclusive declaration” about which bot was best, adding that each showed its own strengths in various locations, “such as language focus, training information and hardware optimization”.

Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, yewiki.org however rather developing in cost-efficient innovation techniques – and bytes-the-dust.com providing localised and improved 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 produced 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, yewiki.org supplies precise and accurate responses to questions about Chinese current events, which gives it an added benefit.

Experts likewise weighed in on their thoughts after using DeepSeek and 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 company Strategy Risks.

“When given a choice, Chinese users desire 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, specifically for Chinese users.

“Ninety per cent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They’re utilizing it for other efficient methods,” Chen said.