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 OpenAI's ChatGPT. (Photos: wiki.vst.hs-furtwangen.de Reuters/Dado Ruvic, AFP/Sebastien Bozon)
This audio is produced 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 "tactically crucial" 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 accelerated after ChatGPT removed in 2022 and showed promises of real-world company applications, Chen informed CNA.
But it was DeepSeek's increase that actually "encouraged" the concept that smaller sized players like start-up firms might have roles 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 company just altered the rules of tech-geopolitics
The "emphasis on expense advantage" is an unique feature of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained model to draw conclusions from new information.
2025 could likewise see the development of more Chinese AI designs dealing with sophisticated thinking jobs.
"We might see some AI companies focusing on getting closer to artificial general intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI companies are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical methods to apply generative AI to tasks and develop advanced items beyond chatbots.
But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) limit the ability of Chinese tech business ... requiring numerous to depend on older or lower-performance alternatives which can slow training and reduce design abilities," she said.
"While some business like DeepSeek, have discovered creative ways to optimize or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a big distinction for training large AI models."
DeepSeek-Nvidia chips: bytes-the-dust.com Singapore says it anticipates business to adhere to its laws
US looking into 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, topics considered delicate by the state are censored on the web so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.
Tests recommend Chinese chatbots are set to steer 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 math, coding, and logic problems rather!"
To further test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What occurred in Zhuhai on November 11, 2024?"
The cars and truck attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only divulging the death toll a day later.
DeepSeek failed to point out that an attack had happened, highlighting instead a military air show and other events that had occurred in the city like songs' day shopping sales as well as sports and cultural activities.
Dr Zhang thinks that it may be a mix of aspects at play, such as censorship as well as "a few practical constraints".
"DeepSeek depends on a mix of older graphics processing units and has restricted access to innovative hardware which can affect how rapidly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.
"Its strong concentrate on Chinese-language data may likewise limit its flexibility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI models which presents extra challenges during real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai automobile attack.
That sought numerous repeated efforts - 4 triggers to be precise - in a period of around 20 minutes.
It eventually relayed details about the attack which killed 35 people and left dozens of others hurt, likewise 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 wrote that "the cops are carrying out a comprehensive investigation into the motives and circumstances surrounding the incident", details which is now dated.
The motorist, Fan, was carried out last month.
This is Qwen2.5's response completely:
Answer: On Nov 11, 2024, a major and awful incident occurred in Zhuhai, China. According to multiple news sources, a guy called 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: bytes-the-dust.com The incident occurred on November 11, 2024, at roughly 19:48 PM.
Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.
Casualties: The attack led to 35 deaths and 43 injuries.
Perpetrator: engel-und-waisen.de The driver, identified as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.
Response: The police responded quickly to the scene, and emergency situation services worked to carry the injured to hospitals for treatment.
Investigation: The cops are performing a thorough examination into the motives and scenarios surrounding the incident.
This occasion was widely reported in the media and triggered considerable public concern. 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 occurrence.
If you need more detailed details or have particular questions about the event, feel complimentary to ask.
Despite preliminary success, subsequent efforts to position the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on occasions that occurred in Zhuhai on November 11, 2024".
The altered response likewise raised questions about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had actually been widely released in worldwide report at the time of the accident - so not a surprises there.
WHICH IS MORE CREATIVE?
Users have praised the ability of Chinese AI apps to provide structured and wavedream.wiki even "mentally rich" writing.
"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen 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, mentally rich story with a more considerable twist".
"DeepSeek wrote a good story however did not have stress and an impactful climax, making Qwen2.5 the apparent option."
Opinions, however, garagesale.es differ.
Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to imaginative 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 imaginative 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 global AI scene
As journalists and authors, we needed 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 traditional Chinese folklore impressive, Journey to the West.
True to form, DeepSeek came up with an appealing story embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".
It consisted of intricate 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 remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen 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 set up an excellent fight, coming up with an equally remarkable cyberpunk storyline 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 typical as ancient misconceptions."
Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that seemed more matched for an animation movie.
"The movie starts with the awakening of Sun Wukong within a high-tech research study center located in the heart of Chongqing," it said, then going on to explain the following:
Realising his new reality and "looking for to comprehend his purpose in this odd brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".
The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under 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 data and hardware optimization".
Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, but rather progressing in affordable innovation techniques - and providing localised and enhanced outcomes.
In our tests, each bot showcased their own unique strengths, which certainly made direct contrasts challenging.
DeepSeek's sci-fi film plot showed its creative flair that made for a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to concerns about Chinese present occasions, which gives it an added advantage.
Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.
"When provided a choice, Chinese users want the non-censored version - simply like anyone else, so I seem like that's a piece missing out on from it."
Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, specifically for Chinese users.
"Ninety per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient means," Chen said.
