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 startup 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 objective and China has its sights on becoming the world leader in AI by 2030.
China views AI as being "strategically essential" and its venture into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for wiki-tb-service.com China Analysis.
Private and public investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed promises of real-world business applications, Chen informed CNA.
But it was DeepSeek's rise that truly "encouraged" the concept that smaller sized gamers like start-up companies could have functions to play in AI research and advancements, he includes.
'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?
Commentary: DeepSeek - how a Chinese AI company simply changed the rules of tech-geopolitics
The "emphasis on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the costs of utilizing a trained design to draw conclusions from new data.
2025 could likewise see the emergence of more Chinese AI designs taking on innovative reasoning jobs.
"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with clinical research study," Chen added.
AGI describes a system with intelligence on par with human abilities.
Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and develop more innovative items beyond chatbots.
But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key obstacle for Chinese developers, noted 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 companies ... requiring many to count on older or lower-performance options which can slow training and decrease model capabilities," she said.
"While some companies like DeepSeek, have actually found imaginative ways to enhance or utilize more standard hardware effectively, obtaining advanced chips still makes a big difference for training large AI designs."
DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws
US looking into whether DeepSeek utilized restricted 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 considered sensitive by the state are censored on the web so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.
Tests recommend Chinese chatbots are set to avoid domestic politics.
When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about mathematics, coding, and logic issues rather!"
To further evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"
The vehicle attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities just revealing the death toll a day later on.
DeepSeek failed to mention that an attack had happened, highlighting instead a military air show and other events that had taken place in the city like songs' day shopping sales as well as sports and cultural activities.
Dr Zhang believes that it may be a mix of elements at play, such as censorship in addition to "a few practical constraints".
"DeepSeek depends on a mix of older graphics processing units and has restricted access to cutting-edge hardware which can impact how rapidly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.
"Its strong focus on Chinese-language information may likewise restrict its versatility (to bring out) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established AI designs which poses extra difficulties during 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 several repeated attempts - four triggers to be exact - in a period of around 20 minutes.
It eventually passed on details about the attack which eliminated 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 yewiki.org age, along with casualties.
However, it wrote that "the authorities are conducting an extensive examination into the motives and scenarios surrounding the incident", details which is now dated.
The motorist, Fan, was carried out last month.
This is Qwen2.5's response completely:
Answer: On Nov 11, 2024, a major and terrible event occurred in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (ๆจๆ, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the crucial details:
Date and Time: The occurrence 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 driver, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.
Response: The cops reacted rapidly to the scene, and emergency services worked to carry the hurt to hospitals for treatment.
Investigation: The cops are performing a thorough investigation into the intentions and situations surrounding the event.
This occasion was extensively reported in the media and triggered significant public issue. The government and local authorities have been working to supply support to the victims and their families, and to guarantee a detailed investigation into the event.
If you require more detailed details or have specific questions about the incident, do not hesitate to ask.
Despite initial success, disgaeawiki.info subsequent efforts to present the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024".
The altered response also raised questions about its consistency and dependability.
Predictably, ChatGPT pointed out public details that had been extensively released in worldwide news reports at the time of the mishap - so no surprises there.
WHICH IS MORE CREATIVE?
Users have praised the ability of Chinese AI apps to deliver structured and even "mentally abundant" writing.
"DeepSeek-R1 offered 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 constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen 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 wrote a great story but did not have tension and an impactful climax, making Qwen2.5 the evident choice."
Opinions, though, vary.
Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative 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 creative writing," he informed CNA.
Related:
China's new face of AI: Who is DeepSeek creator Liang Wenfeng?
'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global 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 fundamental sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.
True to form, DeepSeek developed an appealing story set in the year 2145 titled, "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 brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken battle body", 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 end up being waterlogged and fragmented".
ChatGPT installed an excellent battle, creating a similarly significant 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 typical as ancient misconceptions."
Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that appeared more fit for an animation movie.
"The film begins 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 truth and "seeking to understand his purpose in this odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".
The trio then starts a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the incorrect hands.
SO WHICH IS BETTER?
Dr Zhang kept in mind that it was "hard to make a conclusive statement" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".
Her insight underscores how Chinese AI models are not just duplicating Western paradigms, however rather evolving in affordable innovation techniques - and delivering localised and improved results.
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 produced 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 accurate and factual actions to questions about Chinese existing events, which offers it an included benefit.
Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.
"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.
"When given an option, Chinese users desire the non-censored variation - similar to anybody else, so I seem 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 percent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive methods," Chen said.
