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 produced 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 ending up being the world leader in AI by 2030.

China views AI as being "tactically essential" and its foray into the field has 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 financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the idea that smaller sized players like start-up firms might have roles to play in AI research study and developments, he includes.

'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 simply altered the rules of tech-geopolitics

The "emphasis on expense advantage" is a distinct function of Chinese AI, Chen says, with and reasoning costs - the costs of using a trained model to draw conclusions from new data.

2025 might likewise see the emergence of more Chinese AI models taking on sophisticated thinking jobs.

"We might see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research," Chen added.

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

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

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains an essential difficulty 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 many to depend on older or lower-performance options which can slow training and minimize model abilities," she said.

"While some companies like DeepSeek, have actually discovered imaginative ways to optimize or utilize more fundamental hardware effectively, obtaining innovative chips still makes a huge difference for training huge AI models."

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

US looking into whether DeepSeek utilized limited 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, subjects deemed sensitive by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to stay away from 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 reasoning problems rather!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very 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 media - with authorities only revealing the death toll a day later on.

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

Dr Zhang thinks that it might be a mix of factors at play, such as censorship as well as "a few useful constraints".

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

"Its strong concentrate on Chinese-language data may also restrict its flexibility (to bring out) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more recognized AI designs which postures extra difficulties throughout real-world release."

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

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

It eventually relayed details about the attack which killed 35 individuals and left dozens 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 a thorough examination into the intentions and scenarios surrounding the incident", details which is now dated.

The chauffeur, Fan, bytes-the-dust.com was carried out last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major 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 a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial variety 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 resulted in 35 deaths and 43 injuries.

Perpetrator: genbecle.com The driver, recognized as Fan Weiqiu (male, 62 years old), was captured by the police.

Response: The police reacted quickly to the scene, and emergency services worked to carry the hurt to hospitals for treatment.

Investigation: The authorities are performing an extensive investigation into the motives and situations surrounding the event.

This occasion was extensively reported in the media and caused considerable public concern. The federal government and local authorities have been working to offer support to the victims and their families, and to ensure a detailed examination into the event.

If you need more detailed details or have particular questions about the incident, do not hesitate to ask.

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

The altered response likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been commonly released in global report 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 "emotionally rich" writing.

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

"Qwen2.5 delivered a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek composed an excellent story but lacked stress and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform 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 likewise see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide 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 standard 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 came up with an appealing storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

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

It likewise remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up an excellent fight, coming up with a similarly 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 common as ancient misconceptions."

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

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

Realising his new truth and "seeking to understand his purpose in this unusual brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to protect the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, but rather progressing in cost-efficient innovation techniques - and providing localised and enhanced outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate reactions to questions about Chinese present events, which offers it an added benefit.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - just 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 utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient ways," Chen said.