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 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 objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically essential" and its foray into the field has been "years in the making", said Chen Qiheng, an associated 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 showed promises of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that actually "urged" the concept that smaller players like start-up companies might have functions to play in AI research and developments, he includes.

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

Commentary: DeepSeek - how a Chinese AI company just altered the guidelines of tech-geopolitics

The "focus on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the expenses of utilizing a trained model to reason from brand-new data.

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

"We could see some AI companies focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with scientific research study," Chen included.

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

Chinese AI business are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative AI to tasks and develop more innovative items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key hurdle for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... forcing many to depend on older or lower-performance alternatives which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have found imaginative ways to enhance or use more fundamental hardware efficiently, obtaining innovative chips still makes a big distinction for training huge 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 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 delicate by the state are censored on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.

Tests suggest 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 type of concern yet. Let's chat about mathematics, coding, and reasoning issues instead!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

The car attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities just revealing the death toll a day later.

DeepSeek failed to mention that an attack had actually occurred, highlighting instead a military air show and other events that had actually happened in the city like songs' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing systems and has restricted access to cutting-edge hardware which can affect how quickly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information might also limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more recognized AI models which positions additional difficulties throughout real-world implementation."

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

That was after numerous duplicated efforts - 4 prompts to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 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, along with casualties.

However, it composed that "the authorities are carrying out an extensive examination into the intentions and scenarios surrounding the event", details which is now outdated.

The driver, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and tragic incident happened in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, bytes-the-dust.com resulting in a significant number of casualties. Here are the key details:

Date and Time: The incident occurred on November 11, 2024, at approximately 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, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The authorities responded quickly to the scene, and emergency services worked to transfer the hurt to hospitals for treatment.

Investigation: bytes-the-dust.com The police are carrying out a comprehensive investigation into the intentions and circumstances surrounding the incident.

This event was commonly reported in the media and caused considerable public issue. The government and regional authorities have been working to provide assistance to the victims and their households, and to ensure a detailed investigation into the incident.

If you need more detailed details or have specific concerns about the event, do not hesitate to ask.

Despite preliminary success, subsequent attempts to pose the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".

The transformed reaction likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been extensively published in international news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that builds slowly from curiosity to seriousness, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek wrote a great story however lacked stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as strongly 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, pleasant surprise from Chinese netizens as DeepSeek jolts international AI scene

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

True to form, DeepSeek came up with an engaging 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 also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, 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 "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed an excellent battle, coming up with a similarly remarkable cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his new truth and "looking for to comprehend his purpose in this unusual brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a definitive declaration" about which bot was best, adding that each showed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely duplicating Western paradigms, but rather developing in cost-effective innovation methods - 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 movie plot demonstrated its creative flair that made for a more interesting and creative narrative as compared to Qwen2.5 and setiathome.berkeley.edu ChatGPT's efforts.

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

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

"When provided 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 expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.

"Ninety percent of individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient ways," Chen said.