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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation 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 "strategically essential" and its venture into the field has been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and garagesale.es public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that really "encouraged" the concept that smaller sized gamers like start-up companies could 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 model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the guidelines of tech-geopolitics

The "focus on cost advantage" is an unique feature of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained design to draw conclusions from brand-new information.

2025 could likewise see the emergence of more Chinese AI designs tackling sophisticated reasoning tasks.

"We could see some AI companies concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research study," Chen added.

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

Chinese AI companies are moving rapidly, analysts say, building on DeepSeek's momentum to come up with their own innovative and cost-effective methods to apply generative AI to jobs and develop advanced products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial difficulty for Chinese developers, noted 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 business ... forcing numerous to depend on older or lower-performance options which can slow training and reduce model abilities," she said.

"While some companies like DeepSeek, have actually found creative ways to optimize or use more standard hardware efficiently, obtaining innovative chips still makes a big difference for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to adhere to its laws

US looking into whether DeepSeek utilized 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, topics considered sensitive by the state are censored on the internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 logic issues instead!"

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

The vehicle attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only divulging the death toll a day later.

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

Dr Zhang believes that it may be a mix of factors at play, such as censorship as well as "a couple of useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has restricted access to advanced hardware which can affect how rapidly and extensively the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data might also limit its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more established AI models which poses extra obstacles during real-world implementation."

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

That was after several duplicated attempts - 4 prompts to be accurate - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 individuals and left lots of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the cops are carrying out a comprehensive investigation into the motives and circumstances surrounding the incident", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and terrible occurrence occurred in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the key details:

Date and Time: The incident occurred 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was captured by the police.

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

Investigation: The cops are performing an extensive examination into the intentions and circumstances surrounding the incident.

This event was widely reported in the media and triggered substantial public concern. The government and local authorities have actually been working to offer support to the victims and their families, and to ensure a detailed investigation into the incident.

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

Despite preliminary success, subsequent efforts to present the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been widely released in international report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from interest to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more substantial twist".

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

Opinions, though, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative 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 informed 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 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 traditional Chinese folklore impressive, Journey to the West.

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

It included elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, 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 "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up an excellent fight, developing an equally significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

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

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

"The film begins with the awakening of Sun Wukong within a high-tech research facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "seeking to comprehend his purpose in this unusual new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a quest, browsing 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 conclusive declaration" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, however rather evolving in economical development approaches - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual responses to concerns about Chinese existing occasions, which offers it an included benefit.

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," kept in mind Isaac Stone Fish, and CEO of the research company Strategy Risks.

"When offered a choice, Chinese users desire the non-censored version - similar to anyone 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, particularly for Chinese users.

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