skytechenterprisesolutions

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 created 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 ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" 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 sped up after in 2022 and revealed pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller gamers like start-up firms might have functions to play in AI research and developments, he adds.

'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 just changed the rules of tech-geopolitics

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

2025 might also see the introduction of more Chinese AI models taking on sophisticated thinking tasks.

"We could see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with clinical research," Chen included.

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical methods to use generative AI to tasks and establish more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial hurdle 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) restrict the capability of Chinese tech business ... forcing many to depend on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some companies like DeepSeek, have found innovative ways to optimize or use more standard hardware effectively, obtaining advanced chips still makes a huge difference for training extremely large AI models."

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

US looking into whether DeepSeek utilized limited AI chips obtained through other nations, 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, subjects deemed sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about mathematics, coding, and reasoning problems instead!"

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

The car attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only revealing the death toll a day later.

DeepSeek failed to point out that an attack had happened, highlighting instead a military air program and other occasions that had occurred in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can impact how rapidly and thoroughly the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data may also limit its versatility (to bring out) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more established AI designs which postures additional obstacles throughout real-world implementation."

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

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

It ultimately communicated details about the attack which killed 35 people and left dozens of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the police are conducting an extensive investigation into the intentions and circumstances surrounding the event", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and terrible occurrence took place in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, setiathome.berkeley.edu 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:

Date and Time: The occurrence happened 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 captured by the cops.

Response: The authorities responded quickly to the scene, and emergency situation services worked to transfer the hurt to medical facilities for treatment.

Investigation: The police are performing a thorough examination into the intentions and wiki.dulovic.tech scenarios surrounding the occurrence.

This occasion was commonly reported in the media and triggered considerable public issue. The government and local authorities have been working to supply support to the victims and their families, setiathome.berkeley.edu and to ensure a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to posture the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had actually been widely released in worldwide 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 "mentally rich" writing.

"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

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

"DeepSeek composed an excellent story however did not have stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, differ.

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 tasks, but we can likewise see that it is refraining from doing as strongly as others in imaginative 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 shocks global AI scene

As reporters 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 movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

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

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

It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up an excellent battle, creating a similarly significant cyberpunk storyline 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 rule, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that appeared more fit for an animation movie.

"The film begins with the awakening of Sun Wukong within a modern research study facility 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 strange brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely replicating Western paradigms, but rather developing in cost-efficient innovation techniques - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, systemcheck-wiki.de the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual actions to questions about Chinese existing events, which gives it an added benefit.

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

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

"When given a choice, Chinese users desire the non-censored variation - much like anybody else, so I feel like that's a piece missing from it."

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

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