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'S BEHIND CHINA'S AI BOOM?

Transforming the country 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 important" and its venture into the field has 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 sped up after ChatGPT took off in 2022 and forum.altaycoins.com showed pledges of real-world organization applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the concept that smaller players like start-up companies might have roles to play in AI research study and advancements, 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 company simply changed the guidelines of tech-geopolitics

The "emphasis on cost advantage" is a distinct function of Chinese AI, Chen states, with lower training and inference expenses - the costs of using a to draw conclusions from new information.

2025 could also see the emergence of more Chinese AI models taking on innovative reasoning jobs.

"We might see some AI companies focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and incorporate them with scientific research study," Chen added.

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

Chinese AI business are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own ingenious and affordable ways to use generative AI to jobs and establish more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential 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) limit the capability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some companies like DeepSeek, have discovered innovative ways to optimize or use more fundamental hardware effectively, obtaining cutting-edge chips still makes a big difference for training huge AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates business to adhere to 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, subjects considered sensitive by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and logic problems rather!"

To further test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What occurred in Zhuhai on November 11, 2024?"

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

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

Dr Zhang believes that it may be a mix of aspects at play, such as censorship as well as "a couple of practical constraints".

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

"Its strong concentrate on Chinese-language data may likewise restrict its flexibility (to bring out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more recognized AI models which poses extra obstacles during real-world release."

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

That was after multiple duplicated efforts - 4 prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on 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 authorities are performing a thorough examination into the motives and scenarios surrounding the incident", 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 occurrence occurred in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile 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 collared by the police.

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

Investigation: The authorities are performing an extensive investigation into the motives and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and caused significant public concern. The federal government and regional authorities have actually been working to offer support to the victims and their households, and to guarantee a detailed examination into the occurrence.

If you need more detailed details or have particular concerns about the occurrence, feel complimentary to ask.

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

The altered reaction likewise raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been commonly released in worldwide report at the time of the mishap - 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 introspective tone and smoother psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It provides 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 a great story however did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, vary.

Chen believes that Qwen2.5 does not perform 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 strongly as others in imaginative writing," he told 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 jolts global AI scene

As journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

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

It included intricate 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 brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg club 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 installed a good fight, coming up with an equally dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations change emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that appeared more suited for an animation movie.

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

Realising his new reality and "seeking to comprehend his function in this weird brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "tough to make a definitive declaration" about which bot was best, higgledy-piggledy.xyz adding that each displayed its own strengths in various areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not merely replicating Western paradigms, however rather evolving in affordable development approaches - and providing localised and enhanced results.

In our tests, each bot showcased their own unique 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 creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, wiki.whenparked.com supplies precise and accurate responses to concerns about Chinese existing events, which gives it an included benefit.

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

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

"When offered an option, Chinese users want the non-censored version - 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, particularly for Chinese users.

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