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 game after DeepSeek's success.
Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and it-viking.ch 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 nation 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 "strategically essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, forum.batman.gainedge.org an affiliated scientist 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 organization applications, Chen told CNA.
But it was DeepSeek's increase that really "urged" the idea that smaller players like start-up firms could have roles to play in AI research and advancements, he includes.
'A lot is up in the air': Is Chinese firm DeepSeek's AI model as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI business just changed the guidelines of tech-geopolitics
The "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained design to draw conclusions from brand-new information.
2025 might also see the emergence of more Chinese AI designs dealing with advanced thinking tasks.
"We could see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with clinical research study," Chen added.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI companies are moving rapidly, analysts say, larsaluarna.se constructing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to use 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 a key 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 ... requiring many to rely on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.
"While some companies like DeepSeek, have actually discovered imaginative ways to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a huge difference for training large AI models."
DeepSeek-Nvidia chips: Singapore says it expects business to comply with its laws
US checking out whether DeepSeek utilized 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 web so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.
Tests recommend 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 type of concern yet. Let's chat about math, coding, and logic issues rather!"
To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What happened 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 networks - with authorities only disclosing the death toll a day later.
DeepSeek failed to discuss that an attack had actually taken location, highlighting instead a military air program and other events that had actually occurred in the city like singles' day shopping sales as well as sports and cultural activities.
Dr Zhang thinks that it might be a mix of elements at play, such as censorship in addition to "a few practical constraints".
"DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to innovative hardware which can impact how rapidly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.
"Its strong focus on Chinese-language data may also restrict its flexibility (to bring out) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which positions additional difficulties during real-world release."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai car attack.
That wanted numerous repeated attempts - 4 prompts to be precise - in a period of around 20 minutes.
It ultimately communicated details about the attack which killed 35 individuals and left dozens of others hurt, 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 wrote that "the police are conducting an extensive examination into the motives and scenarios surrounding the occurrence", details which is now dated.
The driver, Fan, was performed last month.
This is Qwen2.5's response in complete:
Answer: On Nov 11, 2024, a major and terrible occurrence took place in Zhuhai, China. According to several news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:
Date and Time: The occurrence occurred on November 11, pipewiki.org 2024, at roughly 19:48 PM.
Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.
Casualties: The attack resulted in 35 deaths and 43 injuries.
Perpetrator: The chauffeur, identified as Fan Weiqiu (male, 62 years of ages), was collared by the police.
Response: The authorities reacted rapidly to the scene, and emergency services worked to carry the injured to health centers for treatment.
Investigation: The police are performing an extensive examination into the intentions and situations surrounding the incident.
This occasion was extensively reported in the media and triggered significant public issue. The federal government and local authorities have been working to provide support to the victims and their households, and to guarantee a detailed investigation into the event.
If you need more detailed details or have particular questions about the occurrence, do not hesitate to ask.
Despite preliminary success, subsequent attempts to posture the same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".
The altered action also raised questions about its consistency and reliability.
Predictably, ChatGPT mentioned public details that had actually been widely released in worldwide news reports 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 rich" writing.
"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more substantial twist".
"DeepSeek wrote a good story however did not have stress and an impactful climax, making Qwen2.5 the obvious choice."
Opinions, though, 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 jobs, however we can also see that it is refraining from doing as strongly as others in creative writing," he told 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 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 basic sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, 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 fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift 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 stolen 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 end up being waterlogged and fragmented".
ChatGPT put up a great battle, creating a similarly significant cyberpunk story 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 guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that seemed more suited for an animation movie.
"The film begins with the awakening of Sun Wukong within a modern research study center located 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 weird new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".
The trio then embarks on a quest, 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 "tough to make a conclusive declaration" about which bot was best, adding that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".
Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, however rather developing in affordable development methods - and delivering localised and improved results.
In our tests, each bot showcased their own distinct strengths, which certainly made direct contrasts challenging.
DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate responses to questions about Chinese present occasions, which gives it an added benefit.
Experts likewise weighed in on their thoughts after utilizing DeepSeek and yewiki.org other Chinese AI apps.
"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, creator wiki.dulovic.tech and CEO of the research study firm Strategy Risks.
"When provided a choice, Chinese users desire the non-censored version - much like anyone else, so I feel like that's a piece missing out on 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 deeper understanding about Xi Jinping or politically delicate subjects. They're using it for other efficient means," Chen said.
