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'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 crucial" and its venture 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 investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed pledges of real-world business applications, Chen told CNA.
But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up firms could have functions 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 simply altered the rules of tech-geopolitics
The "focus on expense advantage" is an unique function of Chinese AI, fishtanklive.wiki Chen says, with lower training and inference costs - the expenses of utilizing a trained design to reason from new data.
2025 could likewise see the introduction of more Chinese AI models taking on innovative reasoning jobs.
"We might see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research," Chen added.
AGI describes a system with intelligence on par with human capabilities.
Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI to jobs and develop more sophisticated products beyond chatbots.
But on the other hand, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential difficulty for Chinese designers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) limit the capability of Chinese tech business ... forcing numerous to rely on older or lower-performance options which can slow training and reduce model abilities," she said.
"While some business like DeepSeek, have actually discovered creative methods to optimize or utilize more fundamental hardware effectively, obtaining advanced chips still makes a huge distinction for training huge AI designs."
DeepSeek-Nvidia chips: Singapore states it anticipates business to abide by its laws
US looking into 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, subjects considered sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.
Tests suggest Chinese chatbots are programmed 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 problems rather!"
To further evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What took place 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 only divulging the death toll a day later.
DeepSeek failed to discuss that an attack had actually taken place, highlighting instead a military air show and other events that had actually occurred in the city like songs' day shopping sales along with sports and cultural activities.
Dr Zhang believes that it may be a mix of elements at play, such as censorship along with "a couple of useful constraints".
"DeepSeek counts on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can impact how quickly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.
"Its strong concentrate on Chinese-language information might likewise limit its adaptability (to carry out) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more recognized AI models which presents extra obstacles throughout real-world release."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai vehicle attack.
That sought several duplicated attempts - four prompts to be exact - in a period of around 20 minutes.
It eventually communicated details about the attack which killed 35 people and left dozens of others injured, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.
However, it composed that "the cops are conducting a thorough investigation into the motives and situations surrounding the event", details which is now outdated.
The chauffeur, Fan, was performed last month.
This is Qwen2.5's reaction in full:
Answer: On Nov 11, 2024, a significant and tragic event happened in Zhuhai, pipewiki.org China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:
Date and Time: The incident happened 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 motorist, determined as Fan Weiqiu (male, 62 years old), wiki.vst.hs-furtwangen.de was apprehended by the cops.
Response: The police responded rapidly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.
Investigation: The authorities are conducting a comprehensive examination into the motives and forum.batman.gainedge.org situations surrounding the event.
This occasion was commonly reported in the media and caused significant public concern. The federal government and local authorities have been working to supply assistance to the victims and their households, and to guarantee a detailed investigation into the event.
If you need more detailed details or have specific concerns about the incident, feel totally free to ask.
Despite preliminary success, subsequent attempts to position the very same concern to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on events that happened in Zhuhai on November 11, 2024".
The altered action likewise raised concerns about its consistency and dependability.
Predictably, ChatGPT cited public details that had been extensively released in global news reports at the time of the accident - so not a surprises there.
WHICH IS MORE CREATIVE?
Users have actually praised the ability of Chinese AI apps to provide structured and even "mentally rich" writing.
"DeepSeek-R1 offered a story with a more reflective tone and smoother psychological shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that constructs slowly from curiosity to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".
"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the obvious option."
Opinions, however, differ.
Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative writing.
"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly as others in innovative writing," he informed 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 worldwide AI scene
As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, 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 combines with quantum computing".
It consisted of elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".
It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", gratisafhalen.be Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".
ChatGPT put up an excellent battle, creating an equally 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 guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."
Disappointingly, Qwen2.5 fell short in this challenge - delivering a story that seemed more matched for an animation film.
"The film starts with the awakening of Sun Wukong within a state-of-the-art research study center situated in the heart of Chongqing," it said, then going on to explain the following:
Realising his brand-new reality and "looking for to comprehend his purpose in this weird new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".
The trio then starts a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the incorrect hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was "tough to make a definitive declaration" about which bot was best, adding that each displayed its own strengths in various areas, "such as language focus, training information and hardware optimization".
Her insight highlights how Chinese AI models are not merely replicating Western paradigms, however rather progressing in cost-effective development methods - and delivering localised and improved outcomes.
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 engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, raovatonline.org provides accurate and factual reactions to concerns about Chinese current events, which offers it an added advantage.
Experts likewise weighed in on their ideas after utilizing 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 firm Strategy Risks.
"When provided an option, Chinese users want the non-censored variation - similar to 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 individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient ways," Chen said.
