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 generated by an AI tool.

Bong Xin Ying

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 becoming the world leader in AI by 2030.

China views AI as being "strategically important" 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 accelerated after ChatGPT removed in 2022 and showed pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized gamers like start-up firms might have functions to play in AI research study and advancements, he includes.

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

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

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the expenses of utilizing a trained model to draw conclusions from brand-new information.

2025 might also see the emergence of more Chinese AI models taking on sophisticated reasoning tasks.

"We could see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.

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

Chinese AI companies are moving quickly, bytes-the-dust.com analysts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable ways to apply generative AI to tasks and develop advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key obstacle for Chinese developers, noted Dr Marina Zhang, archmageriseswiki.com an associate teacher 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 alternatives which can slow training and reduce model abilities," she said.

"While some companies like DeepSeek, have found imaginative methods to enhance or use more basic hardware effectively, obtaining cutting-edge chips still makes a big distinction for training extremely big AI models."

DeepSeek-Nvidia chips: Singapore states it expects business to adhere to 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, subjects deemed delicate by the state are censored on the web 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 suggest Chinese chatbots are programmed to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and reasoning problems rather!"

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

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

DeepSeek failed to discuss that an attack had taken location, highlighting rather a military air show and other events that had actually happened in the city like singles' day shopping sales as well as sports and cultural activities.

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

"DeepSeek depends on a mix of older graphics processing units and has restricted access to advanced hardware which can impact how rapidly and thoroughly the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information may also limit its versatility (to carry out) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established AI designs which presents extra challenges during real-world deployment."

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

That sought several repeated efforts - four prompts to be exact - in a span of around 20 minutes.

It eventually relayed details about the attack which killed 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the authorities are carrying out a thorough investigation into the motives and circumstances surrounding the event", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and awful event happened in Zhuhai, China. According to multiple news sources, a man 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 considerable number of casualties. Here are the key details:

Date and Time: The incident took place 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 old), was nabbed by the cops.

Response: The police responded rapidly to the scene, and emergency services worked to transfer the injured to hospitals for treatment.

Investigation: The police are performing an extensive investigation into the intentions and scenarios surrounding the incident.

This occasion was widely reported in the media and caused significant public issue. The federal government and local authorities have been working to supply assistance to the victims and their families, and to make sure a detailed investigation into the incident.

If you require more detailed details or have particular questions about the event, do not hesitate 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 occurred in Zhuhai on November 11, 2024".

The transformed response likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been commonly released in global 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 "emotionally abundant" writing.

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

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

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

Opinions, however, vary.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and bytes-the-dust.com ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however 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 journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.

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

It consisted of sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a good battle, developing a similarly remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous 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 myths."

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

"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, disgaeawiki.info then going on to explain the following:

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

The trio then embarks on a mission, navigating the streets of Chongqing to safeguard 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 definitive declaration" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather developing in affordable development methods - and providing localised and improved results.

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

DeepSeek's sci-fi motion picture plot demonstrated its creative flair that made for a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate reactions to concerns about Chinese existing occasions, which provides it an added advantage.

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

"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered an option, Chinese users desire the non-censored variation - similar to anyone else, so I seem like that's a piece missing from it."

Independent Beijing-based specialist Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.

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