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 created 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 ending up being 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 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 guarantees of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller gamers like start-up firms could have roles to play in AI research and developments, 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 simply altered the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of utilizing a trained design to draw conclusions from new data.

2025 might also see the introduction of more Chinese AI models tackling sophisticated thinking jobs.

"We could see some AI companies concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods 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 business are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and establish more sophisticated products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key obstacle for Chinese designers, noted 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 business ... requiring many to depend on older or lower-performance alternatives which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have actually discovered imaginative methods to optimize or utilize more basic hardware effectively, obtaining advanced chips still makes a huge difference for training really big AI models."

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

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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 web 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 recommend 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 type of question yet. Let's chat about math, coding, and reasoning problems rather!"

To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same question: "What took place 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 networks - with authorities just revealing the death toll a day later.

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

Dr Zhang thinks that it may 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 systems and has restricted access to innovative hardware which can impact how quickly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information might also restrict its flexibility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more recognized AI models which positions additional obstacles during real-world deployment."

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

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

It ultimately relayed details about the attack which eliminated 35 individuals and left lots of others injured, also going on to list details like the date and pediascape.science time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the police are carrying out an extensive examination into the motives and circumstances surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and awful event occurred in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, wiki.whenparked.com 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the key details:

Date and Time: The event happened on November 11, 2024, 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was captured by the cops.

Response: The police reacted quickly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.

Investigation: The authorities are performing an extensive examination into the motives and circumstances surrounding the occurrence.

This event was extensively reported in the media and triggered considerable public issue. The government and local authorities have actually been working to provide support to the victims and forum.pinoo.com.tr their households, and to make sure a detailed investigation into the incident.

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

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

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

Predictably, ChatGPT mentioned public details that had been commonly published in international report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to deliver structured and even "emotionally rich" writing.

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

"Qwen2.5 delivered a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote a good story but did not have tension and an impactful climax, making Qwen2.5 the evident choice."

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 jobs, but 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, enjoyable 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 standard sci-fi film plot set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

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

It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT put up a great battle, creating an equally significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

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

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

"The motion picture begins with the awakening of Sun Wukong within a high-tech research facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "seeking to comprehend his purpose in this strange new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a conclusive declaration" about which bot was best, adding that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not merely duplicating Western paradigms, but rather developing in cost-effective innovation methods - and providing localised and enhanced outcomes.

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

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

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

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

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

"When offered an option, Chinese users want the non-censored variation - simply like anybody else, so I seem like that's a piece missing out on from it."

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

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