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 lags CHINA'S AI BOOM?

Transforming the country 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 "tactically essential" and its venture into the field has 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 sped up after ChatGPT took off in 2022 and revealed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the idea that smaller sized gamers like start-up firms might have functions to play in AI research study and advancements, he includes.

'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 business simply changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinct function of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained model to reason from brand-new data.

2025 might likewise see the introduction of more Chinese AI models dealing with innovative reasoning tasks.

"We could see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with scientific research," Chen included.

AGI refers to a system with intelligence on par with human capabilities.

Chinese AI business are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a key hurdle for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech companies ... forcing lots of to depend on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have discovered imaginative ways to enhance or utilize more fundamental hardware efficiently, obtaining innovative chips still makes a big difference for training very large AI models."

DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, source says

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 ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to avoid 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 issues rather!"

To even more check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

The vehicle attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just divulging the death toll a day later.

DeepSeek failed to discuss that an attack had actually taken location, highlighting rather a military air program and other occasions that had actually happened in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, wiki.dulovic.tech such as censorship along with "a few useful constraints".

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

"Its strong focus on Chinese-language information might likewise restrict its adaptability (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more recognized AI designs which presents extra challenges throughout real-world implementation."

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

That sought several duplicated attempts - 4 prompts to be accurate - in a period 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, as well as casualties.

However, it wrote that "the police are performing an extensive examination into the motives and circumstances surrounding the occurrence", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and tragic event took place in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

Date and Time: The occurrence occurred on November 11, 2024, at roughly 19:48 PM.

Location: Zhuhai Sports Center, engel-und-waisen.de in the Xiangzhou District of Zhuhai.

Casualties: The attack resulted in 35 deaths and 43 injuries.

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

Response: The authorities reacted quickly to the scene, and emergency services worked to transfer the hurt to healthcare facilities for treatment.

Investigation: The authorities are conducting a comprehensive investigation into the motives and situations surrounding the event.

This occasion was commonly reported in the media and caused considerable public concern. The federal government and regional authorities have actually been working to supply support to the victims and it-viking.ch their families, and to ensure a detailed investigation into the occurrence.

If you require more detailed details or have particular concerns about the event, feel free to ask.

Despite preliminary success, subsequent efforts to present the same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".

The modified reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had been widely published in global news reports 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 deliver structured and even "emotionally abundant" writing.

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

"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vibrant images 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 good story however did not have stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as strongly as others in innovative writing," he told 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 shocks worldwide 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 timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an appealing story set 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 skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight 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 set up a good battle, coming up with an equally significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 difficulty - providing a storyline that appeared more suited for an animation movie.

"The film 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 new truth and "looking for to understand his function in this strange new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive declaration" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not simply reproducing Western paradigms, but rather developing in affordable innovation techniques - and providing localised and improved results.

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

DeepSeek's sci-fi film plot showed its innovative flair that produced a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate responses to questions about Chinese existing occasions, which provides it an added benefit.

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

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

"When provided an option, Chinese users desire the non-censored variation - just like anybody else, so I seem 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, systemcheck-wiki.de especially for Chinese users.

"Ninety percent of people utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient means," Chen said.