the-kn

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 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 "strategically crucial" and its foray 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that really "encouraged" the concept that smaller 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 company DeepSeek's AI design as impactful as it claims?

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

The "focus on cost benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the costs of using a trained model to draw conclusions from brand-new information.

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

"We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with scientific research study," Chen included.

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

Chinese AI companies are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to jobs and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains an essential hurdle for Chinese developers, 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 ability of Chinese tech companies ... requiring lots of to rely on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have discovered imaginative methods to enhance or utilize more standard hardware effectively, obtaining advanced chips still makes a huge distinction for training huge AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to adhere to its laws

US looking into whether DeepSeek utilized restricted 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, topics deemed sensitive by the state are censored on the web so it need to 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 programmed to steer clear of domestic politics.

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

To further test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: "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 greatly censored on Chinese social media - with authorities only divulging the death toll a day later.

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

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

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

"Its strong focus on Chinese-language data might likewise restrict its adaptability (to perform) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the same scale as more established AI models which positions additional obstacles throughout real-world release."

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

That was after multiple repeated attempts - four prompts to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 individuals and wiki.vst.hs-furtwangen.de left lots of others injured, also 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 cops are carrying out a thorough investigation into the intentions and situations surrounding the event", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and tragic occurrence took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the essential details:

Date and Time: The occurrence took place on November 11, 2024, at approximately 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack led to 35 deaths and 43 injuries.

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

Response: it-viking.ch The cops reacted rapidly to the scene, and emergency services worked to transport the injured to hospitals for treatment.

Investigation: The cops are conducting an extensive investigation into the motives and scenarios surrounding the event.

This event was widely reported in the media and triggered substantial public issue. The government and regional authorities have actually been working to supply assistance to the victims and their families, and to make sure a detailed investigation into the incident.

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

Despite initial success, subsequent attempts to pose the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".

The modified action also raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been extensively published in international 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 "mentally abundant" 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 delivered a story that builds slowly from curiosity to seriousness, keeping the reader engaged. It uses an unforeseen 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 substantial twist".

"DeepSeek composed a good story but did not have tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however 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 reporters 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 film 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 engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of sophisticated 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 conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar owner "drowning in debt and vices" and yewiki.org Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a great fight, developing a similarly remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

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

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

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

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

The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive declaration" about which bot was best, adding that each displayed 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, but rather evolving in cost-efficient innovation approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed its creative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, trademarketclassifieds.com unburdened by Chinese censorship constraints, supplies accurate and factual responses to concerns about Chinese present occasions, which gives it an added advantage.

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," noted Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.

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

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

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