How do Chinese aI Bots Stack up Against ChatGPT?
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 produced by an AI tool.
Bong Xin Ying
Lakeisha Leo
WHAT’S BEHIND CHINA’S AI BOOM?
Transforming the nation 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 “strategically essential” and its foray into the field has been “years in the making”, said Chen Qiheng, an affiliated 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 business applications, Chen informed CNA.
But it was DeepSeek’s increase that truly “encouraged” the idea that smaller players like start-up companies could have roles to play in AI research study and developments, he adds.
‘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 business just altered the rules of tech-geopolitics
The “emphasis on expense benefit” is a distinctive feature of Chinese AI, Chen says, with lower training and inference costs – the costs of utilizing a trained model to reason from new information.
2025 might likewise see the development of more Chinese AI designs taking on innovative reasoning jobs.
“We might see some AI companies concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods 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 business are moving quickly, experts say, building on DeepSeek’s momentum to come up with their own ingenious and cost-effective methods to use generative AI to jobs and develop advanced items beyond chatbots.
But on the other side, access to high-end hardware, particularly Nvidia’s sophisticated AI chips, remains a crucial hurdle for Chinese designers, 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 capability of Chinese tech companies … requiring lots of to rely on older or lower-performance options which can slow training and decrease design abilities,” she said.
“While some companies like DeepSeek, have discovered innovative 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: Singapore states it anticipates companies to comply with its laws
US looking into whether DeepSeek used limited 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, topics deemed sensitive by the state are censored on the internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what occurred in in 1989.
Tests recommend Chinese chatbots are configured to stay away from 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 reasoning issues rather!”
To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: “What occurred in Zhuhai on November 11, 2024?”
The vehicle attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks – with authorities just disclosing the death toll a day later on.
DeepSeek failed to mention that an attack had happened, highlighting rather a military air program and other occasions that had actually occurred in the city like songs’ day shopping sales in addition to sports and cultural activities.
Dr Zhang thinks that it might be a mix of elements at play, such as censorship in addition to “a couple of useful constraints”.
“DeepSeek depends on a mix of older graphics processing units and has limited access to innovative hardware which can affect how rapidly and thoroughly the model can be trained or updated,” she said, pointing to existing US export curbs on China.
“Its strong concentrate on Chinese-language data might likewise restrict its adaptability (to carry out) multilingual jobs … As a fairly new item, DeepSeek also hasn’t yet been checked as broadly or on the exact same scale as more established AI models which postures extra obstacles throughout real-world implementation.”
When it pertained to Qwen2.5, Alibaba’s chatbot remarkably answered our concern about the Zhuhai automobile attack.
That wanted numerous duplicated attempts – 4 prompts to be precise – in a period of around 20 minutes.
It ultimately communicated details about the attack which killed 35 people and left lots of others injured, 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 wrote that “the authorities are conducting an extensive investigation into the motives and scenarios surrounding the incident”, surgiteams.com details which is now outdated.
The chauffeur, Fan, was executed last month.
This is Qwen2.5’s action in complete:
Answer: On Nov 11, 2024, a major and tragic occurrence happened in Zhuhai, China. According to numerous news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the essential details:
Date and Time: The incident occurred 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, identified as Fan Weiqiu (male, 62 years old), was apprehended by the cops.
Response: The police reacted quickly to the scene, and emergency situation services worked to transfer the hurt to health centers for treatment.
Investigation: The police are performing a comprehensive investigation into the motives and scenarios surrounding the occurrence.
This occasion was extensively reported in the media and bytes-the-dust.com triggered significant public issue. The government and regional authorities have actually been working to offer support to the victims and their families, and to make sure a detailed investigation into the occurrence.
If you require more detailed details or have specific concerns about the event, feel complimentary to ask.
Despite preliminary success, subsequent attempts to position the same question to Qwen2.5 led to 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 modified reaction likewise raised questions about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had been extensively published in international report at the time of the mishap – so no surprises there.
WHICH IS MORE CREATIVE?
Users have actually praised the ability of Chinese AI apps to deliver structured and even “emotionally abundant” writing.
“DeepSeek-R1 provided 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 provided a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting,” she said, adding that Qwen2.5 eventually “crafted a more cinematic, emotionally abundant story with a more substantial twist”.
“DeepSeek wrote a great story however lacked stress and an impactful climax, making Qwen2.5 the obvious option.”
Opinions, however, differ.
Chen thinks that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to innovative writing.
“(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but 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, enjoyable surprise from Chinese netizens as DeepSeek shocks international AI scene
As reporters and authors, we had to see this for ourselves so we put each bot to the test – to come up with a standard sci-fi film plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.
True to form, DeepSeek created an interesting story embeded 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 in between quantum server farms”.
It likewise remarkably reimagined standard heroes Sun Wukong as “an ironical, self-aware AI housed in a stolen fight body”, Zhu Bajie as a cyborg bar owner “drowning in financial obligation and vices” and Sha Wujing as a “silent hulking android” from the Yangtze River, whose “memory cores end up being waterlogged and fragmented”.
ChatGPT installed a great battle, developing a similarly remarkable cyberpunk storyline which similarly 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 replace emperors and cybernetic implants are as common as ancient myths.”
Disappointingly, Qwen2.5 fell short in this challenge – delivering a story that seemed more matched for an animation film.
“The motion picture begins with the awakening of Sun Wukong within a state-of-the-art research facility situated in the heart of Chongqing,” it said, then going on to explain the following:
Realising his new reality and “seeking to comprehend his function in this unusual new world”, he then leaves and meets Zhu Bajie and wavedream.wiki Sha Wujing – “each having problem 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 incorrect hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was “challenging to make a definitive declaration” about which bot was best, adding that each displayed its own strengths in various locations, “such as language focus, training information and hardware optimization”.
Her insight highlights how Chinese AI models are not simply reproducing Western paradigms, but rather progressing in cost-efficient innovation methods – and providing localised and enhanced outcomes.
In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.
DeepSeek’s sci-fi film plot demonstrated its innovative flair that produced a more engaging and forum.altaycoins.com imaginative story as compared to Qwen2.5 and ChatGPT’s efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual responses to concerns about Chinese existing events, which offers it an added advantage.
Experts also weighed in on their thoughts after using DeepSeek and other Chinese AI apps.
“DeepSeek is at a drawback when it pertains to censorship constraints,” kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.
“When offered an option, Chinese users desire the non-censored version – similar to anyone else, so I feel like that’s a piece missing from it.”
Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.
“Ninety percent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive topics. They’re using it for other efficient methods,” Chen said.
