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 generated 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 becoming the world leader in AI by 2030.
China views AI as being "strategically crucial" 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 removed in 2022 and showed promises of real-world organization applications, Chen informed CNA.
But it was DeepSeek's increase that really "encouraged" the idea that smaller players like start-up companies could have roles to play in AI research study and advancements, he adds.
'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 altered the rules of tech-geopolitics
The "emphasis on expense benefit" is an unique feature of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained design to reason from brand-new information.
2025 could also see the development of more Chinese AI models dealing with sophisticated thinking tasks.
"We might see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research," Chen added.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI business are moving rapidly, experts say, building on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to use AI to tasks and develop advanced products beyond chatbots.
But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a key obstacle 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) limit the ability of Chinese tech business ... forcing numerous to rely on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.
"While some business like DeepSeek, have actually found innovative ways to optimize or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a big distinction for training large AI designs."
DeepSeek-Nvidia chips: Singapore states it expects companies to abide by its laws
US checking out whether DeepSeek utilized limited 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, 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 took place 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 type of concern yet. Let's chat about mathematics, coding, and logic issues instead!"
To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"
The car attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities just revealing the death toll a day later on.
DeepSeek failed to point out that an attack had actually taken location, highlighting rather a military air program and other occasions that had actually happened in the city like songs' day shopping sales as well as sports and cultural activities.
Dr Zhang believes that it might be a mix of factors at play, such as censorship in addition to "a couple of practical constraints".
"DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to innovative hardware which can affect how quickly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.
"Its strong concentrate on Chinese-language information might also restrict its flexibility (to carry out) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized AI models which poses additional obstacles throughout real-world release."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai car attack.
That was after several duplicated attempts - four prompts to be exact - in a period of around 20 minutes.
It eventually communicated details about the attack which killed 35 people and left lots of others hurt, likewise going on to note details like the date and yewiki.org time, details about the assailant including his name and age, in addition to casualties.
However, it wrote that "the authorities are performing a comprehensive investigation into the motives and situations surrounding the incident", details which is now outdated.
The motorist, Fan, was performed last month.
This is Qwen2.5's action completely:
Answer: On Nov 11, 2024, a major and tragic incident took place in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:
Date and Time: The occurrence happened 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the authorities.
Response: The cops responded quickly to the scene, and emergency services worked to carry the hurt to health centers for treatment.
Investigation: The cops are conducting a comprehensive investigation into the intentions and situations surrounding the occurrence.
This occasion was widely reported in the media and triggered considerable public issue. The government and local authorities have been working to provide assistance to the victims and their families, and to ensure a detailed investigation into the occurrence.
If you require more detailed details or have specific concerns about the event, do not hesitate to ask.
Despite preliminary success, subsequent attempts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".
The transformed reaction likewise raised concerns about its consistency and dependability.
Predictably, ChatGPT cited public details that had actually been commonly released in worldwide report at the time of the mishap - so not a surprises there.
WHICH IS MORE CREATIVE?
Users have praised the capability of Chinese AI apps to provide structured and even "emotionally abundant" writing.
"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more substantial twist".
"DeepSeek composed an excellent story however lacked stress and an impactful climax, making Qwen2.5 the evident choice."
Opinions, however, differ.
Chen thinks 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 likewise see that it is refraining from doing as strongly as others in creative writing," he informed CNA.
Related:
China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?
'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts 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 standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.
True to form, DeepSeek developed an engaging story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".
It included fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".
It likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat 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 a great battle, coming up with an equally significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".
"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."
Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that appeared more matched for an animation film.
"The film begins with the awakening of Sun Wukong within a high-tech research study facility situated in the heart of Chongqing," it said, then going on to explain the following:
Realising his new reality and "seeking to understand his purpose in this strange new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".
The trio then embarks on a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the wrong hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was "difficult to make a definitive statement" about which bot was best, including 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 simply duplicating Western paradigms, but rather developing in cost-efficient innovation approaches - and providing localised and improved outcomes.
In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi motion picture plot demonstrated its creative flair that made for a more interesting and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual actions to questions about Chinese present occasions, which offers it an included benefit.
Experts also weighed in on their ideas after using 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 offered an option, Chinese users want the non-censored version - simply like anyone else, so I seem 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, particularly 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 utilizing it for other efficient means," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
mitchel24h4767 edited this page 2025-04-11 20:05:10 +08:00