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 generated 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 goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically essential" and its foray into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world service applications, Chen told CNA.

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

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

Commentary: engel-und-waisen.de DeepSeek - how a Chinese AI business just changed the rules of tech-geopolitics

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

2025 might also see the development of more Chinese AI models dealing with sophisticated thinking tasks.

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

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

Chinese AI companies are moving quickly, experts state, building on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and establish advanced products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial 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 capability of Chinese tech business ... forcing lots of to rely on older or lower-performance alternatives which can slow training and decrease model capabilities," she said.

"While some companies like DeepSeek, have actually discovered creative methods to optimize or use more basic hardware effectively, obtaining innovative chips still makes a big distinction for training extremely large AI designs."

DeepSeek-Nvidia chips: Singapore states it anticipates business to comply with its laws

US checking out whether DeepSeek utilized limited 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 deemed delicate by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred 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 type of concern yet. Let's chat about math, coding, and reasoning problems instead!"

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

The cars and truck attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social media - 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 happened in the city like singles' day shopping sales in addition to sports and cultural activities.

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

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

"Its strong focus on Chinese-language data might likewise limit its flexibility (to carry out) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more established AI models which postures additional obstacles throughout real-world deployment."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our concern about the Zhuhai vehicle attack.

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

It eventually passed on details about the attack which killed 35 individuals and left lots of others injured, also going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the cops are conducting an extensive investigation into the motives and circumstances surrounding the event", bytes-the-dust.com details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a major and awful occurrence occurred in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant 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: forum.altaycoins.com Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The to 35 deaths and 43 injuries.

Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was apprehended by the cops.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to transfer the hurt to healthcare facilities for treatment.

Investigation: The cops are carrying out a comprehensive investigation into the intentions and situations surrounding the event.

This occasion was commonly reported in the media and caused substantial public concern. The federal government and local authorities have actually been working to offer assistance to the victims and their families, and to guarantee a detailed investigation into the occurrence.

If you require more detailed details or have particular concerns about the event, feel totally free to ask.

Despite preliminary success, subsequent attempts to present the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that occurred in Zhuhai on November 11, 2024".

The transformed action also raised concerns about its consistency and dependability.

Predictably, ChatGPT cited public details that had been commonly released in international news reports 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 "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that develops gradually from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek wrote a great story but did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as highly as others in innovative 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 writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore impressive, Journey to the West.

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

It included fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight 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 end up being waterlogged and fragmented".

ChatGPT put up a good battle, coming up with a similarly remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

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

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

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

Realising his new reality and "looking for to understand his purpose in this odd new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a conclusive declaration" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather evolving in cost-effective development techniques - and providing localised and improved outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, bytes-the-dust.com unburdened by Chinese censorship constraints, supplies precise and factual actions to concerns about Chinese existing occasions, which provides it an added advantage.

Experts likewise weighed in on their ideas after utilizing 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 company Strategy Risks.

"When given an option, Chinese users desire 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 deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive ways," Chen said.