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 actually long been President Xi Jinping's goal and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically crucial" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated 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 revealed promises of real-world business applications, Chen told CNA.

But it was that truly "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 company simply altered the rules of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning costs - the costs of using a trained model to reason from brand-new data.

2025 might likewise see the development of more Chinese AI designs tackling sophisticated reasoning 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 models and integrate them with scientific research," Chen added.

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

Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to use generative AI to jobs and establish advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key obstacle for Chinese developers, 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 capability of Chinese tech business ... forcing lots of to depend on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have discovered innovative methods to enhance or utilize more fundamental hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates business to adhere to its laws

US looking into whether DeepSeek used restricted AI chips obtained through other nations, 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 web so it ought to 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 programmed to avoid 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 math, coding, and logic issues instead!"

To further check for accuracy and self-censorship, 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 at first heavily censored on Chinese social media - with authorities just disclosing the death toll a day later.

DeepSeek failed to mention that an attack had taken location, highlighting rather a military air program and other occasions that had occurred in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of elements at play, such as censorship as well as "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact how rapidly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise limit its adaptability (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more recognized AI models which postures extra difficulties during real-world implementation."

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

That sought multiple duplicated efforts - 4 triggers to be exact - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 individuals and left dozens of others hurt, also going on to list 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 conducting a comprehensive investigation into the motives and scenarios surrounding the event", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's action in full:

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

Date and Time: The incident took place on November 11, 2024, at approximately 19:48 PM.

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

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years old), was collared by the cops.

Response: The police responded rapidly to the scene, and emergency services worked to carry the hurt to medical facilities for treatment.

Investigation: The cops are conducting a thorough investigation into the motives and circumstances surrounding the incident.

This event was extensively reported in the media and caused substantial public concern. The federal government and regional authorities have been working to supply assistance to the victims and their families, and to ensure a detailed investigation into the incident.

If you require more detailed details or have particular concerns about the occurrence, do not hesitate to ask.

Despite preliminary success, subsequent attempts to present the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".

The altered response likewise raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had actually been widely released in global report 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 "mentally rich" writing.

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

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

"DeepSeek wrote a great story however lacked stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform 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 likewise see that it is refraining from doing as strongly as others in creative 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 jolts international AI scene

As reporters 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 motion picture plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.

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

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

It also remarkably 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 financial obligation and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a good battle, developing an equally remarkable cyberpunk storyline which likewise 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 challenge - delivering a storyline that seemed more matched for wiki.whenparked.com an animation film.

"The motion picture starts with the awakening of Sun Wukong within a high-tech 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 comprehend his function in this odd new world", 89u89.com he then escapes and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a definitive declaration" about which bot was best, adding that each displayed its own strengths in various locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, but rather progressing in economical innovation approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot demonstrated its creative flair that made for 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, offers precise and accurate actions to questions about Chinese present occasions, which provides it an added benefit.

Experts likewise 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, creator and CEO of the research firm Strategy Risks.

"When given an option, Chinese users want the non-censored version - much like anybody else, so I seem like that's a piece missing out on 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 using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient ways," Chen said.