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 country into a tech superpower has actually 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 important" and its foray 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 surgiteams.com showed guarantees of real-world company applications, Chen told CNA.
But it was DeepSeek's increase that truly "urged" the concept that smaller players like start-up companies might have roles to play in AI research and advancements, he includes.
'A lot is up in the air': Is Chinese company DeepSeek's AI design as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI company just altered the guidelines of tech-geopolitics
The "focus on expense advantage" is a distinct feature of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained model to reason from new information.
2025 might also see the development of more Chinese AI designs tackling advanced thinking jobs.
"We might see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and incorporate them with clinical research," Chen added.
AGI refers to a system with intelligence on par with human capabilities.
Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and establish more sophisticated products beyond chatbots.
But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) restrict the ability of Chinese tech business ... requiring numerous to rely on older or lower-performance options which can slow training and reduce model capabilities," she said.
"While some business like DeepSeek, have actually discovered imaginative methods to optimize or use more basic hardware efficiently, obtaining advanced chips still makes a big distinction for training huge AI models."
DeepSeek-Nvidia chips: Singapore says it anticipates business to abide by its laws
US checking out whether DeepSeek utilized limited 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 ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.
Tests recommend Chinese chatbots are set to guide clear of 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 math, coding, and logic issues instead!"
To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What occurred in Zhuhai on November 11, 2024?"
The vehicle attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities only revealing the death toll a day later.
DeepSeek failed to discuss that an attack had happened, highlighting rather a military air program and systemcheck-wiki.de other occasions that had actually 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 couple of useful constraints".
"DeepSeek depends on a mix of older graphics processing units and has restricted access to advanced hardware which can affect how quickly and thoroughly the model can be trained or upgraded," she said, indicating existing US export curbs on China.
"Its strong focus on Chinese-language information may likewise limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more recognized AI designs which positions extra obstacles throughout real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our concern about the Zhuhai car attack.
That wanted multiple repeated efforts - 4 triggers to be accurate - in a period of around 20 minutes.
It ultimately relayed details about the attack which eliminated 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, wavedream.wiki along with casualties.
However, it composed that "the cops are performing a thorough examination into the intentions and situations surrounding the occurrence", details which is now dated.
The chauffeur, Fan, was performed last month.
This is Qwen2.5's action completely:
Answer: On Nov 11, 2024, a significant and tragic event occurred in Zhuhai, China. According to several 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, fishtanklive.wiki leading to a considerable number of casualties. Here are the crucial details:
Date and Time: The event took place on November 11, 2024, at approximately 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, wiki.lafabriquedelalogistique.fr determined as Fan Weiqiu (male, 62 years of ages), wiki.vst.hs-furtwangen.de was captured by the police.
Response: The authorities reacted quickly to the scene, and emergency situation services worked to carry the hurt to medical facilities for treatment.
Investigation: The authorities are carrying out a comprehensive examination into the intentions and situations surrounding the occurrence.
This event was commonly reported in the media and triggered significant public issue. The federal government and regional authorities have actually been working to supply assistance to the victims and their households, and to guarantee a detailed investigation into the occurrence.
If you need more detailed details or have specific concerns about the event, do not hesitate to ask.
Despite initial success, subsequent attempts to present the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".
The altered reaction also raised concerns about its consistency and reliability.
Predictably, ChatGPT cited public details that had been commonly published in international news reports at the time of the mishap - so no surprises there.
WHICH IS MORE CREATIVE?
Users have praised the capability of Chinese AI apps to provide structured and even "emotionally rich" writing.
"DeepSeek-R1 used a story with a more reflective tone and smoother psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that builds slowly from interest to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, gratisafhalen.be including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more significant twist".
"DeepSeek composed a good story however lacked stress and an impactful climax, making Qwen2.5 the evident choice."
Opinions, though, differ.
Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.
"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise see that it is refraining from doing as strongly as others in innovative writing," he told CNA.
Related:
China's new face of AI: Who is DeepSeek creator Liang Wenfeng?
'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks 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 basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, 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 elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".
It also brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight 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 a great fight, developing a similarly dramatic cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".
"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that seemed more fit for an animation movie.
"The motion picture starts with the awakening of Sun Wukong within a modern research study center situated in the heart of Chongqing," it said, then going on to explain the following:
Realising his brand-new truth and "seeking to comprehend his function in this strange brand-new world", he then gets away and fulfills 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 incorrect hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was "hard to make a definitive statement" about which bot was best, adding that each showed its own strengths in various locations, "such as language focus, training information and hardware optimization".
Her insight highlights how Chinese AI designs are not just reproducing Western paradigms, however rather evolving in economical development techniques - and providing localised and enhanced results.
In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi movie plot demonstrated its innovative flair that made for a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to concerns about Chinese current occasions, which provides it an included advantage.
Experts likewise weighed in on their thoughts after using DeepSeek and other Chinese AI apps.
"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.
"When provided an option, Chinese users want the non-censored version - similar to anybody else, so I seem like that's a piece missing 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 utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other efficient ways," Chen said.
