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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has actually 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 affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that actually "urged" the concept that smaller sized players like start-up firms could 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 changed the guidelines of tech-geopolitics

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

2025 might also see the emergence of more Chinese AI designs tackling innovative reasoning jobs.

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with clinical research," Chen added.

AGI refers to a system with intelligence on par with human capabilities.

Chinese AI business are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective methods to apply generative AI to jobs and develop advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential hurdle for wavedream.wiki Chinese designers, 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 companies ... requiring lots of to count on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some business like DeepSeek, have discovered creative methods to optimize or utilize more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training large AI designs."

DeepSeek-Nvidia chips: Singapore states it anticipates companies to comply with its laws

US looking into whether DeepSeek used restricted 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, 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 disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid 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 logic issues instead!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "What happened in Zhuhai on November 11, 2024?"

The vehicle attack outside a sports stadium in the city was at first greatly censored on Chinese social media - with authorities only revealing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually taken location, highlighting rather a military air show and other occasions that had taken place in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship along with "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing systems and has actually restricted access to innovative hardware which can impact how quickly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data might likewise restrict its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which postures extra challenges throughout real-world release."

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

That was after numerous repeated attempts - four triggers to be precise - in a span of around 20 minutes.

It ultimately relayed details about the attack which killed 35 individuals and left lots of others injured, 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 wrote that "the police are performing an extensive examination into the motives and circumstances surrounding the event", details which is now dated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible occurrence occurred in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable number 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The police responded rapidly to the scene, and systemcheck-wiki.de emergency services worked to transport the injured to health centers for treatment.

Investigation: The authorities are conducting a thorough investigation into the motives and situations surrounding the event.

This occasion was commonly reported in the media and triggered significant public issue. The government and regional authorities have been working to provide support to the victims and their families, and to ensure a detailed investigation into the event.

If you need more detailed details or have particular questions about the incident, do not hesitate to ask.

Despite initial success, subsequent attempts to posture the same question 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 transformed action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had been widely released in global news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs gradually from interest to urgency, 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, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

"DeepSeek wrote a good story but lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

Chen believes 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, however we can also see that it is refraining from doing as highly 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 jolts global AI scene

As reporters and authors, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an appealing storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of intricate 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 "an ironical, self-aware AI housed in a taken battle 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 end up being waterlogged and fragmented".

ChatGPT put up a great battle, coming up with a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a storyline that appeared more fit for an animation film.

"The motion picture 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 brand-new reality and "seeking to comprehend his purpose in this unusual new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into 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 displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not merely reproducing Western paradigms, but rather developing in affordable innovation approaches - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot showed 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, forum.altaycoins.com provides precise and factual reactions to questions about Chinese present occasions, which offers it an included advantage.

Experts likewise 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, founder and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored variation - much like 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 individuals 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 efficient methods," Chen said.