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 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 objective and China has its sights on ending up being the world leader in AI by 2030.
China views AI as being “strategically essential” and its venture 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 accelerated after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen informed CNA.
But it was DeepSeek’s rise that actually “urged” the idea that smaller sized gamers like start-up firms could have functions to play in AI research study and advancements, yewiki.org 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 changed the rules of tech-geopolitics
The “emphasis on cost benefit” is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses – the costs of utilizing a trained design to draw conclusions from new information.
2025 could likewise see the emergence of more Chinese AI designs dealing with advanced thinking jobs.
“We could see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with scientific research,” Chen included.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI companies are moving rapidly, experts state, constructing on DeepSeek’s momentum to come up with their own innovative and economical ways to use generative AI to tasks and establish advanced products beyond chatbots.
But on the other side, access to high-end hardware, especially Nvidia’s sophisticated AI chips, remains a crucial hurdle for Chinese designers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney’s (UTS) Australia-China Relations Institute.
“US export controls (still) limit the capability of Chinese tech business … requiring numerous to count on older or lower-performance options which can slow training and minimize model abilities,” she said.
“While some companies like DeepSeek, have found imaginative ways to optimize or use more basic hardware effectively, obtaining advanced chips still makes a big difference for training huge AI designs.”
DeepSeek-Nvidia chips: systemcheck-wiki.de Singapore says it expects companies to comply with its laws
US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, 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 deemed 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 disputes or tell you what occurred in Tiananmen Square in 1989.
Tests recommend Chinese chatbots are programmed 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 question yet. Let’s chat about math, coding, and logic problems rather!”
To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: “What occurred in Zhuhai on November 11, 2024?”
The vehicle attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media – with authorities just revealing the death toll a day later.
DeepSeek failed to mention that an attack had actually taken location, engel-und-waisen.de highlighting rather a military air show and other events that had actually happened in the city like songs’ day shopping sales in addition to sports and cultural activities.
Dr Zhang believes that it may be a mix of factors at play, such as censorship along with “a few useful constraints”.
“DeepSeek relies on a mix of older graphics processing systems and has limited access to innovative hardware which can impact how rapidly and thoroughly the model can be trained or upgraded,” she said, pointing to existing US export curbs on China.
“Its strong focus on Chinese-language data might also limit its adaptability (to perform) multilingual tasks … As a fairly new product, DeepSeek likewise hasn’t yet been tested as broadly or on the exact same scale as more recognized AI designs which poses extra difficulties during real-world implementation.”
When it pertained to Qwen2.5, Alibaba’s chatbot surprisingly answered our question about the Zhuhai cars and truck attack.
That wanted several repeated attempts – 4 prompts to be exact – in a span of around 20 minutes.
It eventually passed on details about the attack which killed 35 individuals and left lots of others hurt, 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 police are carrying out a thorough examination into the motives and scenarios surrounding the event”, which is now dated.
The motorist, Fan, was carried out last month.
This is Qwen2.5’s action in full:
Answer: On Nov 11, 2024, a major and awful incident occurred in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the crucial details:
Date and Time: The incident happened on November 11, 2024, at roughly 19:48 PM.
Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.
Casualties: forum.altaycoins.com The attack led to 35 deaths and 43 injuries.
Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years old), was captured by the cops.
Response: disgaeawiki.info The police reacted quickly to the scene, and emergency situation services worked to transfer the injured to healthcare facilities for treatment.
Investigation: The cops are conducting an extensive examination into the intentions and circumstances surrounding the occurrence.
This event was widely reported in the media and triggered considerable public issue. The federal government and regional authorities have actually been working to provide support to the victims and their households, and to guarantee a detailed examination into the occurrence.
If you require more detailed details or have specific concerns about the incident, feel totally free to ask.
Despite preliminary success, subsequent attempts to position the same question to Qwen2.5 led to the censors back at work with the reply “I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024”.
The altered reaction likewise raised questions about its consistency and reliability.
Predictably, ChatGPT cited public details that had actually been extensively published in global report at the time of the mishap – so no surprises there.
WHICH IS MORE CREATIVE?
Users have actually praised the capability of Chinese AI apps to provide structured and even “mentally abundant” writing.
“DeepSeek-R1 used a story with a more introspective tone and smoother psychological shifts for a well-paced story,” composed tech writer Amanda Caswell, who specialises in AI.
“Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting,” she said, adding that Qwen2.5 ultimately “crafted a more cinematic, emotionally rich story with a more substantial twist”.
“DeepSeek wrote a great story but lacked tension and an impactful climax, making Qwen2.5 the apparent choice.”
Opinions, though, vary.
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, however we can likewise 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 shocks global AI scene
As reporters and authors, we had to see this for ourselves so we put each bot to the test – to come up with a fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.
True to form, DeepSeek created an appealing story embeded in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism merges with quantum computing”.
It consisted of elaborate settings – smoggy skies “pierced by high-rise buildings”, “holographic lanterns that float above neon-lit streets” and “ancient temples nestled in between quantum server farms”.
It also brilliantly reimagined standard heroes Sun Wukong as “a sarcastic, self-aware AI housed in a taken battle body”, Zhu Bajie as a cyborg club owner “drowning in financial obligation and vices” and Sha Wujing as a “quiet hulking android” from the Yangtze River, whose “memory cores end up being waterlogged and fragmented”.
ChatGPT put up a good battle, developing a similarly dramatic cyberpunk story which likewise reimagined “a ragteam of cyber-enhanced misfits, each mirroring 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 challenge – providing a story that appeared more suited for an animation movie.
“The movie 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 brand-new reality and “looking for to comprehend his purpose in this unusual brand-new world”, he then gets away and satisfies Zhu Bajie and Sha Wujing – “each battling with their own existential crises”.
The trio then starts a quest, browsing the streets of Chongqing to secure the sacred “Eternal Scroll” from falling into the wrong hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was “challenging to make a conclusive statement” about which bot was best, adding that each displayed its own strengths in different locations, “such as language focus, training information and hardware optimization”.
Her insight highlights how Chinese AI designs are not simply replicating Western paradigms, but rather developing in affordable innovation approaches – and delivering localised and enhanced results.
In our tests, each bot showcased their own special strengths, which certainly made direct contrasts challenging.
DeepSeek’s sci-fi movie plot demonstrated its imaginative flair that produced 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 actions to concerns about Chinese current occasions, which provides it an included 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 study firm Strategy Risks.
“When given an option, Chinese users desire the non-censored version – similar to anyone else, so I feel like that’s a piece missing from it.”
Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.
“Ninety per cent of people utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They’re using it for other productive means,” Chen said.
