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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the country 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 accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world service applications, Chen told CNA.

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

'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 changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinct feature of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of utilizing a trained model to reason from new information.

2025 could also see the emergence of more Chinese AI models tackling advanced reasoning tasks.

"We might see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with clinical research study," Chen added.

AGI describes a system with intelligence on par with human abilities.

Chinese AI business are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own innovative and affordable ways to apply generative AI to tasks and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, it-viking.ch remains a crucial difficulty for 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) limit the ability of Chinese tech companies ... forcing many to count on older or lower-performance options which can slow training and decrease design capabilities," she said.

"While some companies like DeepSeek, have discovered imaginative methods to enhance or use more fundamental hardware effectively, obtaining advanced chips still makes a big difference for training very large AI designs."

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

US checking out whether DeepSeek utilized restricted 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, topics deemed sensitive by the state are censored on the internet so it need to come as no 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 set 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 math, coding, and logic problems rather!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very 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 initially heavily censored on Chinese social media - with authorities just divulging the death toll a day later on.

DeepSeek failed to point out that an attack had occurred, highlighting rather a military air show and other events that had occurred in the city like songs' day shopping sales along with 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 counts on a mix of older graphics processing systems and has restricted access to innovative hardware which can impact how rapidly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may also limit its flexibility (to carry out) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more recognized AI designs which postures additional challenges throughout real-world release."

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

That wanted multiple duplicated attempts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately communicated 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 setiathome.berkeley.edu age, in addition to casualties.

However, it wrote that "the police are carrying out a comprehensive examination into the intentions and circumstances surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable number of . Here are the crucial details:

Date and Time: The occurrence occurred on November 11, 2024, at roughly 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 chauffeur, identified as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

Response: The authorities responded rapidly to the scene, and emergency services worked to transport the hurt to medical facilities for treatment.

Investigation: surgiteams.com The cops are performing a thorough investigation into the motives and circumstances surrounding the incident.

This event was commonly reported in the media and triggered considerable public concern. The government and regional authorities have actually been working to offer assistance to the victims and their families, and to make sure a detailed examination into the event.

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

Despite preliminary success, subsequent attempts to present the exact same concern 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 reaction also raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been commonly released in global news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that develops gradually from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote a great story but lacked stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly as others in imaginative writing," he informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks 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 fundamental sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.

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

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

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen fight 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, forum.pinoo.com.tr whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a good battle, creating a similarly remarkable cyberpunk story 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 typical as ancient myths."

Disappointingly, forum.pinoo.com.tr Qwen2.5 fell short in this challenge - providing a storyline that appeared more fit for an animation movie.

"The movie 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 new reality and "looking for to understand his function in this odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the wrong 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 displayed its own strengths in various areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI models are not simply reproducing Western paradigms, but rather progressing in affordable innovation techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi movie plot demonstrated its creative flair that produced a more appealing 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 current events, which gives it an added benefit.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

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

"When provided an option, Chinese users desire the non-censored variation - simply 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, particularly for Chinese users.

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