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 game after DeepSeek's success.
Alibaba's Qwen2.5-Max chatbot, Chinese startup 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 lags CHINA'S AI BOOM?
Transforming the nation 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 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 public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed pledges of real-world company applications, Chen told CNA.
But it was DeepSeek's rise that truly "encouraged" the concept that smaller sized players like start-up firms might have roles to play in AI research study and advancements, 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 changed the guidelines of tech-geopolitics
The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the expenses of utilizing a trained model to draw conclusions from new data.
2025 could also see the introduction of more Chinese AI models dealing with innovative thinking tasks.
"We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with clinical research study," Chen included.
AGI refers to a system with intelligence on par with human abilities.
Chinese AI business are moving quickly, experts state, building on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to apply generative AI to tasks and establish advanced items beyond chatbots.
But on the flip side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial hurdle for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) limit the capability of Chinese tech companies ... forcing numerous to rely on older or lower-performance alternatives which can slow training and lower design abilities," she said.
"While some business like DeepSeek, have found creative ways to optimize or utilize more basic hardware effectively, obtaining innovative chips still makes a huge distinction for training huge AI models."
DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws
US looking into whether DeepSeek used 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, subjects deemed sensitive by the state are censored on the web so it ought to come as no that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.
Tests suggest 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 question 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 very same concern: "What took place in Zhuhai on November 11, 2024?"
The vehicle attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only revealing the death toll a day later on.
DeepSeek failed to mention that an attack had actually happened, highlighting rather a military air program and other occasions that had taken place in the city like singles' day shopping sales as well as sports and cultural activities.
Dr Zhang thinks that it may be a mix of factors at play, such as censorship along with "a couple of useful constraints".
"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to innovative hardware which can affect how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.
"Its strong focus on Chinese-language data may also restrict its flexibility (to carry out) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which positions extra difficulties throughout real-world deployment."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai car attack.
That sought multiple repeated attempts - 4 triggers to be accurate - in a period of around 20 minutes.
It ultimately communicated details about the attack which killed 35 people and left lots of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.
However, it composed that "the authorities are carrying out an extensive investigation into the motives and circumstances surrounding the occurrence", details which is now dated.
The chauffeur, Fan, was executed last month.
This is Qwen2.5's response in complete:
Answer: On Nov 11, 2024, a significant and awful event happened in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the crucial details:
Date and Time: The incident took place on November 11, bytes-the-dust.com 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: archmageriseswiki.com The driver, recognized as Fan Weiqiu (male, 62 years old), was captured by the cops.
Response: The authorities reacted quickly to the scene, and emergency services worked to carry the hurt to medical facilities for treatment.
Investigation: The authorities are carrying out a thorough investigation into the motives and scenarios surrounding the occurrence.
This occasion was extensively reported in the media and caused considerable public issue. The government and regional authorities have been working to supply support to the victims and their families, and to guarantee a detailed examination into the event.
If you need more detailed details or links.gtanet.com.br have specific concerns about the occurrence, feel free to ask.
Despite preliminary success, subsequent efforts to pose the same question to Qwen2.5 led to 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 also raised questions about its consistency and reliability.
Predictably, ChatGPT pointed out public details that had actually been extensively released in global news reports at the time of the accident - 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 builds slowly from curiosity to seriousness, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more significant twist".
"DeepSeek composed a great story however did not have tension and an impactful climax, making Qwen2.5 the evident option."
Opinions, however, vary.
Chen believes 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 jobs, but we can likewise see that it is refraining from doing as strongly as others in imaginative 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 journalists 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 motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, 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 combines with quantum computing".
It included intricate 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 taken battle body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".
ChatGPT put up an excellent battle, coming up with an equally remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".
"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."
Disappointingly, Qwen2.5 fell short in this challenge - providing a storyline 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 facility located in the heart of Chongqing," it said, then going on to explain the following:
Realising his new reality and "seeking to understand his purpose in this strange brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each fighting 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 "tough to make a conclusive 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 designs are not merely reproducing Western paradigms, however rather evolving in affordable development techniques - and delivering localised and improved results.
In our tests, surgiteams.com each bot showcased their own unique strengths, which certainly made direct comparisons challenging.
DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that made for a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual reactions to questions about Chinese current events, which offers it an included benefit.
Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese AI apps.
"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.
"When offered a choice, Chinese users desire the non-censored variation - simply like 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, specifically for Chinese users.
"Ninety per cent of individuals 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 methods," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
Elisa Downes edited this page 2025-02-08 12:51:56 -07:00