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 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 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 essential” 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 financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed pledges of applications, Chen told CNA.

But it was DeepSeek’s rise that truly “encouraged” the concept that smaller sized players like start-up firms could have functions to play in AI research 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 altered the rules of tech-geopolitics

The “emphasis on expense advantage” is a distinctive feature 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 likewise see the development of more Chinese AI models dealing with advanced thinking jobs.

“We could see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate 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 abilities.

Chinese AI companies are moving quickly, experts state, constructing on DeepSeek’s momentum to come up with their own ingenious and economical ways to apply generative AI to jobs and develop more advanced items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia’s sophisticated AI chips, remains a crucial obstacle for Chinese designers, noted Dr Marina Zhang, 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 … forcing lots of to rely on older or lower-performance options which can slow training and decrease model capabilities,” she said.

“While some business like DeepSeek, have actually found innovative methods to enhance or use more standard hardware efficiently, obtaining innovative chips still makes a huge difference for training huge AI models.”

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

US looking into whether DeepSeek used 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, topics deemed 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 disagreements or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to steer clear of domestic politics.

When asked “Who is Xi Jinping”, wiki.asexuality.org DeepSeek’s reply was “Sorry, I’m uncertain how to approach this type of question yet. Let’s chat about mathematics, coding, and logic issues rather!”

To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: “What occurred in Zhuhai on November 11, 2024?”

The car attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only divulging the death toll a day later on.

DeepSeek failed to mention that an attack had actually taken location, highlighting instead a military air program and other occasions that had actually taken place 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, such as censorship along with “a few practical constraints”.

“DeepSeek counts on a mix of older graphics processing systems and has actually limited access to advanced hardware which can affect how rapidly and thoroughly the model can be trained or updated,” she said, indicating existing US export curbs on China.

“Its strong focus on Chinese-language information might likewise limit its flexibility (to bring out) multilingual tasks … As a fairly brand-new item, DeepSeek also hasn’t yet been checked as broadly or on the very same scale as more recognized AI designs which postures additional difficulties throughout real-world implementation.”

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

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

It ultimately passed on details about the attack which killed 35 people and left lots of others hurt, 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 composed that “the cops are conducting an extensive examination into the motives and situations surrounding the incident”, details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5’s response completely:

Answer: On Nov 11, 2024, a significant and tragic event took place in Zhuhai, hb9lc.org China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, disgaeawiki.info 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, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the authorities.

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

Investigation: The authorities are carrying out a comprehensive examination into the intentions and bytes-the-dust.com circumstances surrounding the event.

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

If you require more detailed details or have specific questions about the occurrence, do not hesitate to ask.

Despite preliminary success, subsequent efforts to present the exact same question to Qwen2.5 led to 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 modified response also raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been extensively released in worldwide report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to provide structured and even “mentally rich” writing.

“DeepSeek-R1 provided a story with a more introspective tone and smoother emotional transitions for a well-paced story,” composed tech writer Amanda Caswell, who specialises in AI.

“Qwen2.5 provided a story that builds slowly from curiosity to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery 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 great story however did not have tension and an impactful climax, making Qwen2.5 the evident option.”

Opinions, however, differ.

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

”(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as highly as others in creative writing,” he informed CNA.

Related:

China’s new face of AI: Who is DeepSeek founder Liang Wenfeng?

‘Made in China’: Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international 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 standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, Journey to the West.

True to form, DeepSeek created an interesting story set in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” - which sees “a future where Buddhism combines with quantum computing”.

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

It likewise remarkably reimagined traditional 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 end up being waterlogged and fragmented”.

ChatGPT put up a good fight, systemcheck-wiki.de coming up with a similarly dramatic cyberpunk story which likewise reimagined “a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West”.

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

Disappointingly, Qwen2.5 fell short in this challenge - delivering a story that appeared more matched for an animation film.

“The motion picture begins 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 truth and “looking for to understand his purpose in this weird brand-new world”, he then gets away and satisfies 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 under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was “challenging to make a conclusive statement” about which bot was best, including that each showed its own strengths in various areas, “such as language focus, training data and hardware optimization”.

Her insight underscores how Chinese AI models are not simply replicating Western paradigms, but rather evolving in cost-efficient innovation methods - and delivering localised and improved outcomes.

In our tests, each bot showcased their own special 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 accurate actions to questions about Chinese present occasions, which offers it an added benefit.

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 study firm Strategy Risks.

“When given a choice, Chinese users want the non-censored variation - much like anyone else, so I feel like that’s a piece missing 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 people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They’re using it for other productive methods,” Chen said.