How do Chinese aI Bots Stack up Against ChatGPT?

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’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 “tactically essential” and its venture into the field has actually been “years in the making”, said Chen Qiheng, engel-und-waisen.de 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 pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek’s increase that truly “urged” the concept that smaller players like start-up companies could have roles to play in AI research study and developments, he adds.

‘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 just altered the guidelines of tech-geopolitics

The “emphasis 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 draw conclusions from new information.

2025 might also see the development of more Chinese AI designs tackling advanced reasoning jobs.

“We might see some AI companies concentrating on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with scientific research study,” Chen included.

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

Chinese AI business are moving rapidly, experts say, building on DeepSeek’s momentum to come up with their own innovative and cost-efficient methods to use generative AI to tasks and establish more sophisticated products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia’s innovative AI chips, remains a crucial difficulty for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney’s (UTS) Australia-China Relations Institute.

“US export controls (still) limit the capability of Chinese tech business … requiring lots of to count on older or lower-performance options which can slow training and lower model abilities,” she said.

“While some business like DeepSeek, have actually discovered imaginative methods to enhance or utilize more basic hardware effectively, obtaining cutting-edge chips still makes a huge difference for training huge AI designs.”

DeepSeek-Nvidia chips: Singapore says it expects companies to comply with its laws

US looking into whether DeepSeek utilized limited AI chips obtained through other countries, source states

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, topics considered delicate by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to guide 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 reasoning problems instead!”

To even more test for precision and self-censorship, wiki.dulovic.tech we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: “What occurred in Zhuhai on November 11, 2024?”

The car attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media – with authorities just divulging the death toll a day later.

DeepSeek failed to discuss that an attack had actually taken place, highlighting instead a military air show and other occasions that had in the city like singles’ day shopping sales as well as sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship along with “a few useful constraints”.

“DeepSeek depends on a mix of older graphics processing units and has actually restricted access to cutting-edge 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 concentrate on Chinese-language information may likewise restrict its flexibility (to carry out) multilingual tasks … As a fairly new product, DeepSeek likewise hasn’t yet been tested as broadly or on the same scale as more recognized AI models which postures extra obstacles throughout real-world release.”

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

That sought multiple repeated attempts – four triggers to be accurate – in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 individuals and left lots of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that “the police are carrying out a thorough investigation into the motives and scenarios surrounding the incident”, details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5’s reaction in full:

Answer: On Nov 11, 2024, a significant and terrible event happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the key details:

Date and Time: The incident happened 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 motorist, determined as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The cops are carrying out a comprehensive examination into the motives and circumstances surrounding the incident.

This occasion was extensively reported in the media and triggered significant public concern. The government and local authorities have actually been working to provide support to the victims and their households, and to make sure a detailed examination into the incident.

If you require more detailed details or have particular questions about the occurrence, feel totally free to ask.

Despite initial success, subsequent efforts to pose the very same question to Qwen2.5 resulted in the censors back at work with the reply “I do not have specific details on occasions that took place in Zhuhai on November 11, 2024”.

The modified action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had been commonly released in worldwide news reports at the time of the mishap – so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver 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,” wrote tech writer Amanda Caswell, who specialises in AI.

“Qwen2.5 delivered a story that constructs gradually from interest to seriousness, keeping the reader engaged. It uses an unforeseen 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 rich story with a more substantial twist”.

“DeepSeek wrote a good story but did not have stress and an impactful climax, making Qwen2.5 the apparent choice.”

Opinions, however, vary.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative 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 creative writing,” he told CNA.

Related:

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

‘Made in China’: Pride, pleasant surprise from Chinese netizens as DeepSeek shocks global AI scene

As journalists and writers, we had 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 interesting story embeded in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

It consisted of elaborate 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 standard heroes Sun Wukong as “an ironical, self-aware AI housed in a taken battle 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, whose “memory cores end up being waterlogged and fragmented”.

ChatGPT set up a great fight, creating a similarly significant cyberpunk story which similarly reimagined “a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West”.

“This is a world where AI deities rule, corporations change emperors and cybernetic implants are as typical as ancient myths.”

Disappointingly, Qwen2.5 fell short in this challenge – providing a story that seemed more fit for an animation movie.

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

Realising his brand-new reality and “looking for to understand his purpose in this odd brand-new world”, he then leaves and satisfies Zhu Bajie and Sha Wujing – “each battling with their own existential crises”.

The trio then starts a quest, navigating the streets of Chongqing to safeguard the spiritual “Eternal Scroll” from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was “hard to make a definitive statement” about which bot was best, adding that each displayed its own strengths in various areas, “such as language focus, training information and hardware optimization”.

Her insight highlights how Chinese AI models are not merely duplicating Western paradigms, but rather evolving in cost-effective development methods – and delivering localised and genbecle.com enhanced outcomes.

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

DeepSeek’s sci-fi movie plot demonstrated its imaginative flair that made for a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to concerns about Chinese existing occasions, which provides it an included benefit.

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

“DeepSeek is at a drawback when it pertains to censorship constraints,” noted Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.

“When provided a choice, Chinese users want 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 people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They’re utilizing it for other efficient ways,” Chen said.