How do Chinese aI Bots Stack up Against ChatGPT?
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 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 “strategically essential” and its foray into the field has been “years in the making”, said Chen Qiheng, wavedream.wiki an affiliated scientist at the Asia Society Policy Institute’s Center for China Analysis.
Private and public financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world organization applications, Chen informed CNA.
But it was DeepSeek’s rise that really “urged” the idea that smaller sized players like start-up companies could have functions to play in AI research study and advancements, he adds.
‘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 cost benefit” is a distinctive function of Chinese AI, Chen says, with lower training and reasoning expenses – the expenses of using a trained design to draw conclusions from new information.
2025 could also see the emergence of more Chinese AI models tackling sophisticated thinking jobs.
“We might see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with scientific research,” Chen added.
AGI refers to a system with intelligence on par with human abilities.
Chinese AI business are moving quickly, analysts say, constructing on DeepSeek’s momentum to come up with their own ingenious and cost-efficient methods to apply generative AI to tasks and develop advanced products beyond chatbots.
But on the other side, access to high-end hardware, particularly Nvidia’s advanced AI chips, remains a key obstacle 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 business … forcing numerous to depend on older or lower-performance options which can slow training and reduce design capabilities,” she said.
“While some business like DeepSeek, have found innovative ways to optimize or utilize more basic hardware efficiently, obtaining innovative chips still makes a big distinction for training huge AI designs.”
DeepSeek-Nvidia chips: Singapore says it anticipates business to comply with its laws
US looking into whether DeepSeek utilized 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 deemed 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 disputes or tell you what took place in Tiananmen Square in 1989.
Tests recommend 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 mathematics, coding, and reasoning problems rather!”
To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, larsaluarna.se Qwen2.5 and bytes-the-dust.com ChatGPT the very same concern: “What occurred in Zhuhai on November 11, 2024?”
The cars and truck attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks – with authorities just divulging the death toll a day later.
DeepSeek failed to discuss that an attack had occurred, highlighting instead a military air program and other events that had actually occurred in the city like singles’ day shopping sales along with sports and cultural activities.
Dr Zhang believes that it may be a mix of factors at play, such as censorship in addition to “a couple of practical constraints”.
“DeepSeek counts on a mix of older graphics processing systems and has limited access to innovative hardware which can impact how rapidly and extensively the model can be trained or updated,” she said, indicating existing US export curbs on China.
“Its strong concentrate on Chinese-language data might likewise restrict its adaptability (to carry out) multilingual tasks … As a fairly brand-new product, DeepSeek also hasn’t yet been tested as broadly or on the exact same scale as more recognized AI designs which poses extra difficulties throughout real-world release.”
When it pertained to Qwen2.5, Alibaba’s chatbot surprisingly addressed our concern about the Zhuhai car attack.
That sought multiple repeated efforts – 4 triggers to be exact – in a span of around 20 minutes.
It ultimately 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 age, as well as casualties.
However, it wrote that “the cops are conducting a thorough investigation into the motives and scenarios surrounding the event”, details which is now dated.
The motorist, Fan, was performed last month.
This is Qwen2.5’s action in complete:
Answer: On Nov 11, 2024, a significant and awful occurrence occurred in Zhuhai, China. According to multiple news sources, a male 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 substantial variety of casualties. Here are the key details:
Date and Time: The event 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 motorist, determined as Fan Weiqiu (male, 62 years of ages), was captured by the authorities.
Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the injured to healthcare facilities for treatment.
Investigation: The authorities are performing an extensive investigation into the motives and scenarios surrounding the incident.
This occasion was extensively reported in the media and triggered significant public issue. The government and regional authorities have been working to offer assistance to the victims and their households, and to make sure a detailed investigation into the event.
If you require more or have specific concerns about the occurrence, feel complimentary to ask.
Despite preliminary success, subsequent efforts to pose the exact same concern to Qwen2.5 led to the censors back at work with the reply “I don’t have particular details on occasions that took place in Zhuhai on November 11, 2024”.
The modified response also raised questions about its consistency and reliability.
Predictably, ChatGPT cited public details that had been extensively released in international report 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 provided a story with a more reflective tone and smoother psychological transitions for a well-paced story,” composed tech author Amanda Caswell, who specialises in AI.
“Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting,” she said, including that Qwen2.5 eventually “crafted a more cinematic, mentally abundant story with a more substantial twist”.
“DeepSeek composed a good story however did not have stress and an impactful climax, making Qwen2.5 the obvious option.”
Opinions, however, vary.
Chen thinks that Qwen2.5 does not perform as strongly 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 imaginative writing,” he told CNA.
Related:
China’s brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?
‘Made in China’: Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide 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 fundamental sci-fi movie 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 storyline embeded in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism merges with quantum computing”.
It included fancy settings – smoggy skies “pierced by high-rise buildings”, “holographic lanterns that drift above neon-lit streets” and “ancient temples nestled between quantum server farms”.
It likewise brilliantly reimagined standard heroes Sun Wukong as “a sarcastic, self-aware AI housed in a taken fight body”, Zhu Bajie as a cyborg bar 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 fight, developing an equally significant cyberpunk storyline which similarly reimagined “a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West”.
“This is a world where AI deities rule, corporations replace 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 movie.
“The film starts with the awakening of Sun Wukong within a modern research center situated in the heart of Chongqing,” it said, then going on to explain the following:
Realising his new reality and “seeking to comprehend his function in this odd new world”, he then escapes and meets Zhu Bajie and Sha Wujing – “each struggling with their own existential crises”.
The trio then embarks on a quest, browsing the streets of Chongqing to protect the spiritual “Eternal Scroll” from falling under the wrong hands.
SO WHICH IS BETTER?
Dr Zhang noted that it was “difficult 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 highlights how Chinese AI designs are not simply reproducing Western paradigms, but rather progressing in cost-efficient innovation techniques – and delivering localised and improved results.
In our tests, each bot showcased their own unique strengths, which certainly made direct comparisons challenging.
DeepSeek’s sci-fi film plot demonstrated its imaginative flair that produced a more interesting and imaginative story as compared to Qwen2.5 and ChatGPT’s efforts.
Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual reactions to questions about Chinese existing events, which offers it an included benefit.
Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.
“DeepSeek is at a disadvantage when it pertains to censorship constraints,” kept in mind Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.
“When offered a choice, Chinese users want the non-censored variation – similar to anybody else, so I seem like that’s a piece missing from it.”
Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.
“Ninety percent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate subjects. They’re utilizing it for other efficient methods,” Chen said.
