GitLab

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 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 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 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and wiki.lafabriquedelalogistique.fr revealed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller sized players like start-up companies might have functions to play in AI research and advancements, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinctive feature of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of using a trained design to draw conclusions from new data.

2025 might also see the introduction of more Chinese AI models dealing with innovative thinking jobs.

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

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

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

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential 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) restrict the capability of Chinese tech companies ... requiring many to count on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have actually discovered imaginative ways to optimize or use more basic hardware effectively, obtaining advanced chips still makes a huge difference for training large AI designs."

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

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

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 considered delicate by the state are censored on the web so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.

Tests suggest 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 math, coding, and logic issues rather!"

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

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

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

Dr Zhang thinks that it may be a mix of elements at play, such as censorship in addition to "a couple of practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can affect how quickly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may also limit its versatility (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more recognized AI designs which postures extra difficulties during real-world deployment."

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

That sought numerous duplicated efforts - 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 dozens of others injured, likewise going on to note details like the date and time, archmageriseswiki.com details about the assailant including his name and age, as well as casualties.

However, it composed that "the cops are performing a thorough examination into the motives and scenarios surrounding the occurrence", details which is now outdated.

The driver, larsaluarna.se Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, it-viking.ch male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the key details:

Date and Time: The incident occurred 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 driver, identified as Fan Weiqiu (male, 62 years old), was collared by the police.

Response: The police responded quickly to the scene, and emergency situation services worked to transport the hurt to hospitals for treatment.

Investigation: The police are performing a thorough examination into the motives and situations surrounding the incident.

This occasion was widely reported in the media and triggered considerable public issue. The federal government and regional authorities have been working to supply support to the victims and their households, and to ensure a detailed investigation into the event.

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

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

The transformed reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been widely released 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 provide structured and even "mentally rich" writing.

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

"Qwen2.5 provided a story that builds slowly from curiosity to urgency, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

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

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out 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 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, enjoyable surprise from Chinese netizens as DeepSeek shocks global AI scene

As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main from the classic 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 merges with quantum computing".

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

It also brilliantly 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, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a great battle, developing a similarly dramatic cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that seemed more matched for an animation film.

"The movie begins with the awakening of Sun Wukong within a state-of-the-art research center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "looking for to understand his purpose in this strange brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to protect 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 conclusive statement" 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 highlights how Chinese AI models are not simply reproducing Western paradigms, however rather evolving in cost-effective innovation techniques - and providing localised and improved results.

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

DeepSeek's sci-fi movie plot demonstrated its creative 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 accurate and factual actions to questions about Chinese existing events, which offers it an added advantage.

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," kept in mind Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users want the non-censored variation - similar to anybody else, so I seem 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 much deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive means," Chen said.