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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually 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 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 removed in 2022 and showed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's increase that really "encouraged" the concept that smaller sized players like start-up companies could 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 business just altered the rules of tech-geopolitics

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

2025 could likewise see the introduction of more Chinese AI models tackling sophisticated reasoning jobs.

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

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

Chinese AI companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI to tasks and develop more sophisticated products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial difficulty for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech companies ... requiring many to rely on older or lower-performance alternatives which can slow training and lower design capabilities," she said.

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

DeepSeek-Nvidia chips: Singapore states it anticipates companies to abide by its laws

US looking into whether DeepSeek used 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, topics deemed delicate by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests recommend 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 mathematics, coding, and logic issues instead!"

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

The vehicle attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had actually taken place, highlighting rather a military air show and other events that had actually happened 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 couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has actually restricted access to innovative hardware which can affect how quickly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data may also limit its versatility (to bring out) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the exact same scale as more recognized AI designs which presents additional obstacles during real-world implementation."

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

That sought several duplicated attempts - 4 triggers to be exact - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 people and left lots of others injured, likewise 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 authorities are performing a comprehensive investigation into the intentions and situations surrounding the incident", disgaeawiki.info details which is now outdated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's response in full:

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

Date and Time: The occurrence took place on November 11, 2024, at around 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 chauffeur, recognized as Fan Weiqiu (male, 62 years old), was captured by the police.

Response: The police responded quickly to the scene, and emergency situation services worked to carry the injured to healthcare facilities for treatment.

Investigation: The police are carrying out an extensive investigation into the intentions and circumstances surrounding the occurrence.

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

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

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

The modified response also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been widely released in worldwide news reports at the time of the mishap - so not a 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 introspective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs slowly 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 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, 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 creator Liang Wenfeng?

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

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

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

It consisted of elaborate 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 remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a great fight, coming up with an equally significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 obstacle - providing a storyline that seemed more matched for an animation film.

"The movie starts 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 comprehend his purpose in this strange brand-new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a definitive statement" 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 models are not simply replicating Western paradigms, but rather developing in cost-efficient development techniques - and delivering localised and improved results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and accurate responses to concerns about Chinese current events, which provides it an included benefit.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When given an option, Chinese users desire the non-censored variation - much 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, especially 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 topics. They're utilizing it for other productive methods," Chen said.