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 video 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 lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually 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 "strategically important" and its foray into the field has actually been "years in the making", said Chen Qiheng, an associated 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 showed pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that truly "encouraged" the idea that smaller players like start-up companies could have roles to play in AI research and advancements, he includes.

'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 business simply altered the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinct function of Chinese AI, wiki.whenparked.com Chen says, with lower training and reasoning expenses - the expenses of using a trained design to reason from brand-new data.

2025 might likewise see the emergence of more Chinese AI models tackling advanced reasoning tasks.

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

AGI describes a system with on par with human capabilities.

Chinese AI companies are moving quickly, analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to use generative AI to jobs and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains an essential obstacle for Chinese developers, noted Dr Marina Zhang, an associate teacher 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 depend on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have discovered imaginative ways to enhance or utilize more basic hardware efficiently, obtaining innovative chips still makes a big distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates business to adhere to its laws

US checking out 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 internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed 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 math, coding, and logic problems rather!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and bio.rogstecnologia.com.br ChatGPT the exact same concern: "What occurred 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 only disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually happened, highlighting rather a military air program 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 factors at play, such as censorship along with "a few useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has limited access to cutting-edge 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 data may also limit its adaptability (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the very 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 addressed our concern about the Zhuhai vehicle attack.

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

It ultimately passed on details about the attack which killed 35 people and left lots of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the police are performing a comprehensive investigation into the motives and situations surrounding the event", details which is now outdated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and tragic event took place in Zhuhai, China. According to multiple news sources, larsaluarna.se a man named Fan Weiqiu (樊某, male, bytes-the-dust.com 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the key details:

Date and wiki.vst.hs-furtwangen.de Time: The occurrence took place on November 11, 2024, at approximately 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and bytes-the-dust.com 43 injuries.

Perpetrator: The motorist, identified as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The cops reacted quickly to the scene, and emergency situation services worked to transfer the injured to medical facilities for treatment.

Investigation: The authorities are carrying out an extensive examination into the intentions and circumstances surrounding the event.

This occasion was widely reported in the media and caused substantial public issue. The federal government and local authorities have been working to supply assistance to the victims and their households, and to guarantee a detailed investigation into the event.

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

Despite initial success, subsequent efforts to position the same concern to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that occurred in Zhuhai on November 11, 2024".

The modified reaction also raised concerns about its consistency and dependability.

Predictably, ChatGPT cited public details that had been widely 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 "emotionally abundant" writing.

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

"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, however, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to innovative 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 innovative 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 reporters 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 motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, Journey to the West.

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

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

ChatGPT installed a good battle, developing a similarly dramatic cyberpunk storyline 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 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 suited for an animation movie.

"The movie begins with the awakening of Sun Wukong within a modern research study center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "seeking to understand his purpose in this weird new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a definitive statement" 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 underscores how Chinese AI models are not just replicating Western paradigms, but rather evolving in affordable innovation methods - and delivering localised and improved outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual actions to questions about Chinese present occasions, which gives it an included advantage.

Experts also 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 trademarketclassifieds.com CEO of the research study company Strategy Risks.

"When given a choice, Chinese users desire the non-censored version - simply like anyone else, so I feel 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, specifically for Chinese users.

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