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 ending up being the world leader in AI by 2030.
China views AI as being "tactically important" and its foray into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.
Private and forum.pinoo.com.tr public investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world organization applications, Chen informed CNA.
But it was DeepSeek's rise that actually "urged" the concept that smaller sized players like start-up companies might have functions to play in AI research and developments, he adds.
'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 simply altered the rules of tech-geopolitics
The "focus on cost advantage" is a distinctive function of Chinese AI, Chen states, with lower training and reasoning costs - the expenses of utilizing a trained model to reason from brand-new data.
2025 might likewise see the introduction of more Chinese AI models tackling innovative reasoning tasks.
"We might see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with scientific research study," Chen added.
AGI describes a system with intelligence on par with human abilities.
Chinese AI companies are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to use generative AI to jobs and establish more sophisticated items beyond chatbots.
But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial 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) limit the ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance options which can slow training and decrease model abilities," she said.
"While some business like DeepSeek, have actually discovered creative methods to enhance or use more standard hardware efficiently, obtaining innovative chips still makes a big distinction for training huge AI models."
DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws
US checking out whether DeepSeek utilized limited AI chips obtained through other countries, source says
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 delicate by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in in 1989.
Tests suggest Chinese chatbots are programmed to steer clear of 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 logic problems rather!"
To even more 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 automobile attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities only revealing the death toll a day later on.
DeepSeek failed to mention that an attack had actually happened, highlighting instead a military air program and other occasions that had occurred in the city like singles' day shopping sales along with sports and cultural activities.
Dr Zhang thinks that it may be a mix of aspects at play, such as censorship along with "a couple of practical constraints".
"DeepSeek counts on a mix of older graphics processing systems and has actually limited access to advanced hardware which can affect how quickly and extensively the model can be trained or updated," she said, pointing to 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 product, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more established AI designs which presents additional obstacles throughout real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai cars and truck attack.
That sought multiple duplicated attempts - four triggers to be exact - in a span of around 20 minutes.
It ultimately relayed details about the attack which killed 35 individuals 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, in addition to casualties.
However, it wrote that "the authorities are conducting an extensive investigation into the motives and scenarios surrounding the event", details which is now outdated.
The chauffeur, Fan, was carried out last month.
This is Qwen2.5's reaction in complete:
Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:
Date and Time: The incident occurred on November 11, 2024, at around 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 services worked to transfer the hurt to hospitals for treatment.
Investigation: The authorities are performing a thorough investigation into the intentions and circumstances surrounding the incident.
This event was widely reported in the media and triggered significant public issue. The federal government and local authorities have been working to supply support to the victims and their families, and to make sure a detailed investigation into the event.
If you need more detailed details or have specific concerns about the incident, do not hesitate to ask.
Despite initial success, subsequent attempts to position the very same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that occurred 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 widely released in worldwide report at the time of the mishap - so not a surprises there.
WHICH IS MORE CREATIVE?
Users have praised the capability of Chinese AI apps to deliver structured and even "mentally rich" writing.
"DeepSeek-R1 used a story with a more reflective tone and smoother psychological transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.
"Qwen2.5 provided a story that builds gradually from curiosity to urgency, keeping the reader engaged. It offers an unanticipated 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, mentally abundant story with a more significant twist".
"DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the evident choice."
Opinions, though, differ.
Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 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 shocks international AI scene
As reporters 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 film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, 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 consisted of intricate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".
It also remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club 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 set up a great fight, coming up with an equally dramatic cyberpunk story which likewise 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 change emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that seemed more fit for an animation movie.
"The movie starts with the awakening of Sun Wukong within a high-tech research facility situated 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 weird brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".
The trio then embarks on a mission, browsing the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the incorrect hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was "tough to make a definitive declaration" about which bot was best, adding that each showed its own strengths in different locations, "such as language focus, training information and hardware optimization".
Her insight underscores how Chinese AI models are not just duplicating Western paradigms, however rather developing in cost-efficient development approaches - and providing localised and improved outcomes.
In our tests, each bot showcased their own distinct strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi movie plot showed its innovative flair that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate reactions to questions about Chinese current events, which provides it an included benefit.
Experts likewise weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.
"When provided a choice, Chinese users desire the non-censored version - just like anyone else, so I seem 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, especially for Chinese users.
"Ninety percent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient ways," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
launaneilson81 edited this page 2025-04-03 13:41:11 +00:00