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 startup 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'S BEHIND 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 ending up being the world leader in AI by 2030.
China views AI as being "tactically crucial" and its foray into the field has been "years in the making", said Chen Qiheng, an associated scientist 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 revealed pledges of real-world service applications, Chen told CNA.
But it was DeepSeek's rise that truly "urged" the concept that smaller gamers like start-up firms might have roles to play in AI research study and developments, 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 company just changed the rules of tech-geopolitics
The "focus on expense benefit" is an unique function of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained design to reason from new information.
2025 could also see the introduction of more Chinese AI designs taking on innovative thinking tasks.
"We might see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others focus 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 rapidly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative AI to jobs and establish advanced products beyond chatbots.
But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key 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 ... forcing many to depend on older or lower-performance options which can slow training and minimize design abilities," she said.
"While some companies like DeepSeek, have found innovative ways to optimize or use more standard hardware effectively, obtaining cutting-edge chips still makes a big distinction for training huge AI designs."
DeepSeek-Nvidia chips: Singapore states it anticipates companies to comply with its laws
US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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 disagreements or inform you what happened in Tiananmen Square in 1989.
Tests suggest Chinese chatbots are configured to guide clear of domestic politics.
When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of question yet. Let's chat about mathematics, coding, and logic problems instead!"
To even more evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What occurred in Zhuhai on November 11, 2024?"
The automobile attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just divulging the death toll a day later on.
DeepSeek failed to discuss that an attack had actually taken place, highlighting rather a military air show and other events that had taken place 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 elements at play, such as censorship in addition to "a couple of practical constraints".
"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to advanced hardware which can impact how rapidly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.
"Its strong focus on Chinese-language data may also restrict its adaptability (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which presents additional obstacles throughout real-world deployment."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our concern about the Zhuhai automobile attack.
That wanted numerous duplicated attempts - 4 triggers to be accurate - in a span of around 20 minutes.
It eventually communicated details about the attack which killed 35 individuals and left dozens of others hurt, engel-und-waisen.de also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.
However, it wrote that "the cops are carrying out a thorough investigation into the motives and situations surrounding the incident", details which is now dated.
The chauffeur, Fan, was performed last month.
This is Qwen2.5's action in complete:
Answer: On Nov 11, 2024, a significant and terrible incident took place in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the crucial details:
Date and Time: The incident took place 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: The driver, recognized as Fan Weiqiu (male, 62 years old), was captured by the police.
Response: The authorities responded quickly to the scene, and emergency situation services worked to carry the hurt to hospitals for treatment.
Investigation: The authorities are carrying out a thorough investigation into the motives and scenarios surrounding the occurrence.
This occasion was commonly reported in the media and triggered considerable public concern. The federal government and local authorities have been working to offer support to the victims and their households, and to ensure a detailed examination into the occurrence.
If you need more detailed details or have particular concerns about the incident, feel free to ask.
Despite initial success, subsequent attempts to present the very same concern 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 modified reaction also raised questions about its and dependability.
Predictably, ChatGPT mentioned public details that had been widely published in global news reports 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 deliver structured and even "mentally abundant" writing.
"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that builds gradually from curiosity to urgency, 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, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".
"DeepSeek composed a good story but lacked stress and an impactful climax, making Qwen2.5 the obvious choice."
Opinions, though, vary.
Chen believes that Qwen2.5 does not perform as strongly 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 highly as others in imaginative 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 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 motion picture plot embeded in the futuristic megacity of Chongqing, systemcheck-wiki.de featuring main characters from the classic Chinese folklore legendary, Journey to the West.
True to form, DeepSeek came up with an engaging story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".
It consisted of sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".
It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat 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 an excellent battle, developing a similarly significant 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 typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that seemed more suited for an animation movie.
"The motion picture starts 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 truth and "seeking to comprehend his function in this unusual brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".
The trio then starts a mission, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was "challenging to make a definitive statement" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".
Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather evolving in cost-effective development methods - and providing localised and improved outcomes.
In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi movie plot demonstrated its creative flair that made for archmageriseswiki.com a more appealing and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, it-viking.ch the more recognized ChatGPT, wiki.lafabriquedelalogistique.fr unburdened by Chinese censorship constraints, provides accurate and accurate responses to concerns about Chinese current events, engel-und-waisen.de which offers it an added benefit.
Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.
"When offered an option, Chinese users want the non-censored version - simply like anybody else, so I seem like that's a piece missing out on from it."
Independent Beijing-based specialist 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 utilizing it for other productive ways," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
Delia Aguirre edited this page 2025-02-15 12:47:20 +00:00