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 startup 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 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 "tactically important" 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 systemcheck-wiki.de China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that actually "urged" the concept that smaller players like start-up companies could have functions to play in AI research and advancements, he adds.

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

Commentary: DeepSeek - how a Chinese AI company just altered the guidelines of tech-geopolitics

The "focus on expense advantage" is an unique function of Chinese AI, Chen says, with lower training and reasoning expenses - the expenses of utilizing a trained model to draw conclusions from brand-new data.

2025 could also see the development of more Chinese AI models taking on advanced reasoning jobs.

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

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

Chinese AI companies are moving quickly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential obstacle for Chinese designers, 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 business ... forcing lots of to count on older or lower-performance options which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have found innovative ways to enhance or utilize more basic hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates business to abide by its laws

US checking out whether DeepSeek used limited AI chips obtained through other countries, 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, subjects considered sensitive by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured 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 reasoning problems instead!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred 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 media - with authorities only disclosing the death toll a day later.

DeepSeek failed to mention that an attack had actually taken place, highlighting instead a military air program and other events that had actually occurred in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it may be a mix of elements at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing systems 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, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise restrict its adaptability (to carry out) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more recognized AI models which postures extra challenges throughout real-world deployment."

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

That sought multiple duplicated efforts - four triggers to be exact - in a span of around 20 minutes.

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

However, setiathome.berkeley.edu it wrote that "the police are conducting a comprehensive examination into the motives and circumstances surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's response completely:

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

Date and wavedream.wiki Time: The event happened on November 11, 2024, at approximately 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, recognized as Fan Weiqiu (male, 62 years old), was apprehended by the cops.

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

Investigation: The authorities are carrying out a thorough examination into the motives and circumstances surrounding the occurrence.

This occasion was commonly reported in the media and caused considerable public issue. The federal government and regional authorities have been working to offer assistance to the victims and their families, and to ensure a detailed examination into the event.

If you require more detailed details or engel-und-waisen.de have particular questions about the event, feel totally free to ask.

Despite initial success, subsequent efforts to position the same concern 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 altered action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely released in global report 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 provided a story with a more reflective tone and smoother emotional transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that builds gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek composed a good story but lacked 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 innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as highly as others in creative writing," he told CNA.

Related:

China's new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts global AI scene

As journalists and it-viking.ch authors, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, DeepSeek came up with 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 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 also remarkably 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 "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a good fight, developing a similarly remarkable 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 guideline, corporations change emperors and cybernetic implants are as common as ancient myths."

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

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

Realising his new truth and "seeking to understand his function in this strange brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather progressing in cost-efficient development approaches - and providing localised and improved results.

In our tests, each bot showcased their own special strengths, wiki.vst.hs-furtwangen.de which certainly made challenging.

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual actions to concerns about Chinese current events, which gives it an included benefit.

Experts also 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 a choice, 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 expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.

"Ninety percent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient ways," Chen said.