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: 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 goal and China has its sights on becoming the world leader in AI by 2030.
China views AI as being "strategically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, yewiki.org an affiliated scientist at the Asia Society Policy Institute's Center for China Analysis.
Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed pledges of real-world service applications, Chen informed CNA.
But it was DeepSeek's rise that actually "urged" the concept that smaller gamers like start-up companies might have roles to play in AI research study and advancements, 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 "focus on cost advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the expenses of using a trained model to draw conclusions from brand-new data.
2025 could also see the development of more Chinese AI designs taking on jobs.
"We might see some AI companies 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 study," Chen added.
AGI describes a system with intelligence on par with human abilities.
Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and archmageriseswiki.com cost-effective ways to apply generative AI to tasks and develop advanced products beyond chatbots.
But on the other hand, access to high-end hardware, especially 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) restrict the ability of Chinese tech business ... requiring many to depend on older or lower-performance alternatives which can slow training and decrease design abilities," she said.
"While some business like DeepSeek, have actually discovered creative methods to optimize or use more basic hardware efficiently, obtaining advanced chips still makes a big distinction for training really big AI designs."
DeepSeek-Nvidia chips: Singapore states it expects business to adhere to its laws
US looking into whether DeepSeek used restricted AI chips obtained through other countries, source states
So how do Chinese AI bots compare against ChatGPT? We put them to the test.
WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?
In China, topics considered sensitive by the state are censored on the internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.
Tests suggest Chinese chatbots are set to stay away from 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 further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and engel-und-waisen.de ChatGPT the exact same question: "What happened in Zhuhai on November 11, 2024?"
The cars and truck attack outside a sports arena 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 mention that an attack had actually occurred, highlighting rather a military air program and other events that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.
Dr Zhang believes that it might be a mix of elements at play, such as censorship as well as "a couple of useful constraints".
"DeepSeek relies on a mix of older graphics processing systems and has actually limited access to advanced hardware which can affect how quickly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.
"Its strong focus on Chinese-language data might also limit its flexibility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more recognized AI models which positions extra obstacles throughout real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai vehicle attack.
That wanted multiple repeated attempts - 4 triggers to be precise - in a period of around 20 minutes.
It ultimately passed on details about the attack which eliminated 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, along with casualties.
However, it composed that "the police are carrying out an extensive examination into the motives and scenarios surrounding the occurrence", details which is now obsoleted.
The motorist, Fan, was carried out last month.
This is Qwen2.5's reaction in full:
Answer: On Nov 11, 2024, a major and terrible occurrence took place in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the key details:
Date and Time: 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 resulted in 35 deaths and 43 injuries.
Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.
Response: The authorities reacted rapidly to the scene, and emergency situation services worked to carry the injured to health centers for treatment.
Investigation: The police are performing a comprehensive investigation into the motives and situations surrounding the occurrence.
This occasion was commonly reported in the media and caused considerable public concern. The government and regional authorities have actually been working to provide assistance to the victims and their households, and to ensure a detailed examination into the occurrence.
If you need more detailed details or have particular questions about the occurrence, do not hesitate to ask.
Despite initial success, subsequent attempts to posture the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that happened in Zhuhai on November 11, 2024".
The modified action likewise raised concerns about its consistency and reliability.
Predictably, ChatGPT pointed out public details that had actually been commonly released in international news reports at the time of the mishap - so no surprises there.
WHICH IS MORE CREATIVE?
Users have praised the ability of Chinese AI apps to deliver structured and even "mentally rich" writing.
"DeepSeek-R1 used a story with a more introspective tone and smoother psychological transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that constructs slowly from interest to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".
"DeepSeek wrote a good story however lacked tension and an impactful climax, making Qwen2.5 the obvious option."
Opinions, however, differ.
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 creative writing," he told CNA.
Related:
China's brand-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 standard sci-fi movie 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 interesting story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".
It included sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".
It likewise remarkably reimagined standard heroes Sun Wukong as "an ironical, 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 end up being waterlogged and fragmented".
ChatGPT put up an excellent battle, creating a similarly dramatic cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching 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 myths."
Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that seemed more fit for an animation movie.
"The motion picture begins with the awakening of Sun Wukong within a high-tech research 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 understand his function in this odd new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".
The trio then starts a quest, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the wrong hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was "challenging to make a definitive declaration" 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 merely duplicating Western paradigms, however rather progressing in affordable innovation approaches - and providing localised and improved outcomes.
In our tests, each bot showcased their own unique strengths, which certainly made direct contrasts challenging.
DeepSeek's sci-fi movie plot showed its imaginative flair that produced a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and factual reactions to concerns about Chinese present occasions, which provides it an added advantage.
Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a downside 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 variation - just 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, especially for Chinese users.
"Ninety per cent of people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other productive methods," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
Alyce McKinlay edited this page 2025-04-09 21:24:47 +02:00