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 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 becoming the world leader in AI by 2030.
China views AI as being "strategically essential" and its venture into the field has 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 sped up after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen told CNA.
But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized 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 design as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI company simply altered the rules of tech-geopolitics
The "emphasis on expense advantage" is a distinctive function of Chinese AI, Chen states, with lower training and inference expenses - the costs of using a trained design to reason from new information.
2025 could likewise see the development of more Chinese AI designs dealing with advanced thinking tasks.
"We might see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research," Chen added.
AGI refers to 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 innovative and cost-effective methods to apply generative AI to tasks and establish more innovative items beyond chatbots.
But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial obstacle for Chinese developers, noted Dr Marina Zhang, an associate professor at University of (UTS) Australia-China Relations Institute.
"US export controls (still) limit the ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance alternatives which can slow training and decrease model capabilities," she said.
"While some business like DeepSeek, have actually found creative methods 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 states it anticipates business to comply with its laws
US looking into whether DeepSeek used limited AI chips obtained through other nations, source states
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 deemed delicate by the state are censored on the web so it need to 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 kind of question yet. Let's chat about mathematics, coding, and reasoning issues instead!"
To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What occurred in Zhuhai on November 11, 2024?"
The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only disclosing the death toll a day later on.
DeepSeek failed to point out that an attack had occurred, highlighting rather a military air program and other occasions that had actually taken place in the city like songs' day shopping sales along with sports and cultural activities.
Dr Zhang thinks that it may be a mix of elements at play, such as censorship as well as "a few useful constraints".
"DeepSeek counts on a mix of older graphics processing units and has actually restricted access to advanced hardware which can impact how rapidly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.
"Its strong concentrate on Chinese-language information may likewise limit its flexibility (to perform) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established AI models which presents additional difficulties throughout real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai vehicle attack.
That wanted multiple repeated efforts - 4 prompts to be accurate - in a span of around 20 minutes.
It eventually passed on details about the attack which eliminated 35 people and left dozens of others injured, also going on to note 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 conducting a thorough examination into the intentions and circumstances surrounding the occurrence", details which is now obsoleted.
The chauffeur, Fan, was performed last month.
This is Qwen2.5's action in complete:
Answer: On Nov 11, 2024, a major and tragic event took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the key details:
Date and Time: The occurrence happened 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 of ages), was captured by the cops.
Response: The cops reacted quickly to the scene, and emergency services worked to carry the hurt to hospitals for treatment.
Investigation: The cops are performing an extensive investigation into the intentions and situations surrounding the event.
This event was commonly reported in the media and triggered substantial public issue. The government and regional authorities have actually been working to offer assistance to the victims and their households, and to guarantee a detailed investigation into the occurrence.
If you require more detailed details or have specific questions about the incident, do not hesitate to ask.
Despite initial success, subsequent efforts to pose the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that happened in Zhuhai on November 11, 2024".
The modified reaction likewise raised questions about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had actually been commonly published in international 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 "emotionally rich" writing.
"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that constructs gradually from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".
"DeepSeek composed an excellent story but lacked tension and an impactful climax, making Qwen2.5 the obvious choice."
Opinions, though, differ.
Chen thinks 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 jobs, but we can also see that it is refraining from doing as strongly as others in creative writing," he informed CNA.
Related:
China's new face of AI: Who is DeepSeek founder Liang Wenfeng?
'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks global 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, featuring main characters from the classic Chinese folklore legendary, Journey to the West.
True to form, DeepSeek came up with an interesting story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".
It included 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 remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".
ChatGPT installed a good fight, coming up with 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 rule, corporations change emperors and cybernetic implants are as common as ancient myths."
Disappointingly, Qwen2.5 fell short in this obstacle - providing a storyline that appeared more matched 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 "seeking to comprehend his function in this odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".
The trio then embarks on a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the incorrect hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was "tough to make a conclusive statement" about which bot was best, wiki.lafabriquedelalogistique.fr including that each displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".
Her insight highlights how Chinese AI models are not just reproducing Western paradigms, however rather developing in cost-effective development approaches - and providing localised and enhanced outcomes.
In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi movie plot showed its creative flair that made for a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to questions about Chinese existing events, which gives it an added benefit.
Experts likewise weighed in on their ideas after using DeepSeek and other Chinese AI apps.
"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.
"When given an option, Chinese users desire the non-censored variation - simply like anybody else, so I feel 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, particularly for Chinese users.
"Ninety per cent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive methods," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
raleightomholt edited this page 2025-04-06 00:25:03 +09:00