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'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 ending up being 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 affiliated scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT removed in 2022 and engel-und-waisen.de revealed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller players like start-up companies might have roles to play in AI research and developments, he adds.

'A lot is up in the air': Is Chinese company DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company simply altered the rules of tech-geopolitics

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of using a trained model to reason from brand-new information.

2025 could likewise see the emergence of more Chinese AI designs tackling advanced thinking jobs.

"We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research," Chen included.

AGI describes a system with intelligence on par with human capabilities.

Chinese AI companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective ways to apply generative AI to jobs and establish more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential hurdle 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 rely on older or lower-performance options which can slow training and minimize design capabilities," she said.

"While some companies like DeepSeek, have discovered creative methods to optimize or utilize more basic hardware effectively, obtaining advanced chips still makes a big difference for training large AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to abide by its laws

US checking out whether DeepSeek utilized limited AI chips obtained through other nations, source states

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, subjects considered sensitive by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened 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 mathematics, coding, and reasoning problems rather!"

To further 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 cars and truck attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just revealing the death toll a day later.

DeepSeek failed to point out that an attack had actually taken location, highlighting instead a military air program and other occasions that had actually happened in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it may be a mix of factors at play, wiki.vst.hs-furtwangen.de such as censorship along with "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing systems and has limited access to innovative 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 focus on Chinese-language information may also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI designs which postures extra obstacles during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai automobile attack.

That wanted several repeated attempts - 4 triggers to be exact - in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 people and left lots of others injured, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the cops are performing a comprehensive investigation into the motives and scenarios surrounding the event", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible event took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant variety of casualties. Here are the crucial details:

Date and Time: The incident happened on November 11, 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: The motorist, pipewiki.org recognized as Fan Weiqiu (male, 62 years of ages), was collared by the police.

Response: The police reacted rapidly to the scene, and emergency services worked to carry the injured to medical facilities for treatment.

Investigation: The police are conducting an extensive examination into the intentions and circumstances surrounding the event.

This occasion was commonly reported in the media and triggered considerable public concern. The government and local authorities have been working to offer support to the victims and their families, and to ensure a detailed examination into the occurrence.

If you require more detailed details or have specific questions about the incident, feel free to ask.

Despite initial success, subsequent attempts to pose the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that happened in Zhuhai on November 11, 2024".

The altered response also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been widely published in worldwide report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to provide structured and even "mentally abundant" writing.

"DeepSeek-R1 provided a story with a more introspective tone and smoother psychological shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops gradually from curiosity to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more substantial twist".

"DeepSeek wrote a good story but did not have stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as highly as others in creative writing," he told 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 jolts 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 fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an engaging storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a good battle, coming up with 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 guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that seemed more suited for an animation movie.

"The movie starts with the awakening of Sun Wukong within a state-of-the-art research study center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "seeking to comprehend his function in this weird brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect 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 locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, but rather developing in cost-efficient development approaches - and engel-und-waisen.de providing localised and enhanced results.

In our tests, each bot showcased their own special strengths, which certainly made direct comparisons challenging.

DeepSeek's sci-fi film plot showed its imaginative flair that made for a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate reactions to questions about Chinese current occasions, which offers it an added advantage.

Experts likewise weighed in on their ideas 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, creator and CEO of the research firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored version - 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, particularly for wavedream.wiki Chinese users.

"Ninety per cent of people utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive ways," Chen said.