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 video 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 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 foray 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and showed guarantees of real-world organization applications, Chen informed CNA.

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

'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 business just changed the rules of tech-geopolitics

The "emphasis on expense benefit" is an unique feature of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of utilizing a trained model to reason from brand-new information.

2025 might likewise see the development of more Chinese AI models dealing with sophisticated thinking jobs.

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

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

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

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial 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) limit the ability of Chinese tech companies ... requiring many to depend on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.

"While some companies like DeepSeek, have discovered innovative ways to enhance or utilize more standard hardware efficiently, obtaining advanced chips still makes a big difference for training really large AI designs."

DeepSeek-Nvidia chips: Singapore says it expects business to comply with its laws

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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, topics considered delicate by the state are censored on the web so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to guide clear of 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 mathematics, coding, and reasoning problems rather!"

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

The automobile attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only disclosing the death toll a day later on.

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

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

"DeepSeek depends on a mix of older graphics processing systems and has limited access to advanced 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 concentrate on Chinese-language data might likewise restrict its flexibility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated 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 remarkably answered our concern about the Zhuhai cars and truck attack.

That was after multiple repeated efforts - 4 triggers to be precise - in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 people and left dozens of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the authorities are carrying out an extensive examination into the intentions and situations surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and tragic event happened in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the crucial details:

Date and Time: The event occurred on November 11, 2024, at around 19:48 PM.

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

Casualties: The to 35 deaths and 43 injuries.

Perpetrator: The driver, determined as Fan Weiqiu (male, 62 years of ages), was apprehended by the authorities.

Response: The cops reacted rapidly to the scene, and emergency services worked to transport the hurt to healthcare facilities for treatment.

Investigation: bytes-the-dust.com The authorities are carrying out a thorough investigation into the intentions and circumstances surrounding the event.

This event was widely reported in the media and triggered considerable public issue. The government and local authorities have actually been working to provide support to the victims and their households, and to guarantee a detailed investigation into the occurrence.

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

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

The transformed action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been widely released in worldwide report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to provide structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more considerable twist".

"DeepSeek composed an excellent story but did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 creative writing," he told CNA.

Related:

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

'Made in China': Pride, pleasant 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 fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created 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 likewise remarkably 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 financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a great battle, creating a similarly significant cyberpunk story 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 change emperors and cybernetic implants are as typical as ancient misconceptions."

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

"The motion picture starts with the awakening of Sun Wukong within a modern research study 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 odd new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a conclusive statement" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not simply reproducing Western paradigms, however rather developing in cost-effective development methods - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate reactions to concerns about Chinese present events, which gives it an included advantage.

Experts likewise weighed in on their thoughts 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, creator and CEO of the research study firm Strategy Risks.

"When given an option, Chinese users desire the non-censored version - just like anyone 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 people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive methods," Chen said.