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, wiki.eqoarevival.com AFP/Sebastien Bozon)

This audio is produced 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 important" and its foray into the field has actually 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 accelerated after ChatGPT took off in 2022 and showed guarantees of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that actually "urged" the idea that smaller players like start-up firms might have functions to play in AI research and developments, 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 just changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the costs of utilizing a trained design to reason from brand-new information.

2025 might likewise see the emergence of more Chinese AI models dealing with sophisticated thinking tasks.

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

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

Chinese AI business are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to use generative AI to tasks and establish more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial obstacle 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 companies ... forcing lots of to count on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some business like DeepSeek, have found creative ways to optimize or use more basic hardware efficiently, obtaining innovative chips still makes a huge difference for training huge AI designs."

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

US checking out whether DeepSeek utilized limited AI chips obtained through other nations, source states

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 sensitive by the state are censored on the internet so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured 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 logic issues rather!"

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

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

DeepSeek failed to discuss that an attack had actually taken location, highlighting instead a military air program and other occasions that had actually 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 few useful constraints".

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

"Its strong concentrate on Chinese-language information might likewise limit its versatility (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more recognized AI models which presents extra challenges throughout real-world implementation."

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

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

It ultimately relayed details about the attack which eliminated 35 individuals and left dozens 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 composed that "the authorities are conducting an extensive investigation into the motives and situations surrounding the incident", details which is now outdated.

The motorist, Fan, was executed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a significant and terrible incident happened in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, wakewiki.de resulting in a considerable number of casualties. Here are the essential details:

Date and Time: The occurrence happened 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 driver, determined as Fan Weiqiu (male, 62 years old), was captured by the cops.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.

Investigation: The cops are conducting a thorough investigation into the motives and situations surrounding the occurrence.

This event was commonly reported in the media and triggered significant public concern. The government and regional authorities have been working to provide support to the victims and their families, and to make sure a detailed investigation into the occurrence.

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

Despite initial success, subsequent efforts to pose the very same concern to Qwen2.5 led to 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 reaction likewise raised concerns about its consistency and hb9lc.org dependability.

Predictably, ChatGPT cited public details that had been commonly released in worldwide 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 used a story with a more reflective tone and smoother psychological transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more substantial twist".

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

Opinions, though, differ.

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

Related:

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

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

As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.

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

It consisted of - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar 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 good battle, coming up with a similarly remarkable 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 replace emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that appeared more fit for an animation film.

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

Realising his new truth and "looking for to understand his function in this unusual new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not just duplicating Western paradigms, but rather developing in cost-efficient innovation approaches - and providing localised and enhanced results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual responses to questions about Chinese existing events, which offers it an added benefit.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind 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 seem like that's a piece missing from it."

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

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