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 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 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 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 sped up after ChatGPT removed in 2022 and showed promises of real-world service applications, Chen told CNA.
But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized gamers like start-up companies might 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 just altered the rules of tech-geopolitics
The "emphasis on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained model to draw conclusions from brand-new data.
2025 could also see the emergence of more Chinese AI designs tackling innovative thinking jobs.
"We could see some AI companies concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with clinical research study," Chen added.
AGI refers to a system with intelligence on par with human capabilities.
Chinese AI business are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective methods to use generative AI to tasks and establish more sophisticated items beyond chatbots.
But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key obstacle for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.
"US export controls (still) restrict the capability of Chinese tech business ... forcing lots of to depend on older or lower-performance alternatives which can slow training and reduce design abilities," she said.
"While some companies like DeepSeek, have discovered imaginative methods to optimize or use more fundamental hardware efficiently, obtaining advanced chips still makes a huge difference for training large AI models."
DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws
US checking out 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 considered delicate 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 inform you what occurred in Tiananmen Square in 1989.
Tests recommend Chinese chatbots are configured to avoid 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 mathematics, coding, and reasoning issues rather!"
To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What happened in Zhuhai on November 11, 2024?"
The cars and truck attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities just divulging the death toll a day later on.
DeepSeek failed to mention that an attack had actually occurred, highlighting instead a military air show and other events that had actually occurred in the city like songs' day shopping sales in addition to 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 useful constraints".
"DeepSeek depends on a mix of older graphics processing units and has actually limited access to innovative hardware which can affect how quickly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.
"Its strong focus on Chinese-language data may likewise limit its adaptability (to carry out) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more established AI models which presents additional challenges throughout real-world implementation."
When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our concern about the Zhuhai automobile attack.
That was after several duplicated efforts - four prompts to be accurate - in a span of around 20 minutes.
It ultimately passed on details about the attack which eliminated 35 people and left dozens of others hurt, likewise 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 police are performing a thorough investigation into the motives and circumstances surrounding the occurrence", details which is now dated.
The driver, Fan, was executed last month.
This is Qwen2.5's action completely:
Answer: On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the key details:
Date and Time: The event took place 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 of ages), was nabbed by the authorities.
Response: The authorities responded quickly to the scene, and emergency services worked to carry the hurt to medical facilities for treatment.
Investigation: The police are conducting an extensive examination into the motives and situations surrounding the occurrence.
This event was widely reported in the media and triggered considerable public issue. The government and regional authorities have actually been working to provide assistance to the victims and their families, and to guarantee a detailed investigation into the incident.
If you require more detailed details or have particular concerns about the event, do not hesitate to ask.
Despite preliminary success, subsequent efforts to position the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that happened in Zhuhai on November 11, 2024".
The altered reaction also raised concerns about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had actually been widely released 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 deliver structured and even "mentally abundant" writing.
"DeepSeek-R1 used a story with a more reflective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.
"Qwen2.5 delivered a story that builds gradually from interest to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more substantial twist".
"DeepSeek composed a great story however lacked stress and an impactful climax, making Qwen2.5 the obvious option."
Opinions, though, differ.
Chen thinks 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 tasks, but we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he told CNA.
Related:
China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?
'Made in China': Pride, enjoyable surprise from Chinese netizens as global AI scene
As reporters and writers, 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 embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.
True to form, DeepSeek came up with an appealing story embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".
It included elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".
It likewise remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub 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 put up an excellent fight, creating 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 rule, corporations change emperors and cybernetic implants are as typical as ancient myths."
Disappointingly, classificados.diariodovale.com.br Qwen2.5 fell short in this challenge - providing a story that seemed more matched for an animation film.
"The movie 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 new reality and "seeking to understand 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 starts a quest, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was "tough to make a definitive statement" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".
Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, but rather evolving 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 motion picture plot demonstrated its creative flair that made for a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.
Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to concerns about Chinese present events, which provides it an included benefit.
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, founder and CEO of the research firm Strategy Risks.
"When given an option, Chinese users desire the non-censored variation - much like anyone else, so I feel like that's a piece missing out on from it."
Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.
"Ninety per cent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive means," Chen said.
1
How do Chinese aI Bots Stack up Against ChatGPT?
Aretha Willhite edited this page 2025-02-23 16:28:37 +00:00