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 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 lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated researcher 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 revealed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller gamers like start-up companies could have roles to play in AI research 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 simply changed the rules of tech-geopolitics

The "emphasis on cost benefit" is an unique function of Chinese AI, Chen says, with lower training and inference expenses - the expenses of utilizing a trained model to reason from new information.

2025 could likewise see the emergence of more Chinese AI designs dealing with advanced reasoning jobs.

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

AGI describes a system with intelligence on par with human abilities.

Chinese AI business are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective methods to use generative AI to jobs and develop more advanced products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key difficulty 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 ability of Chinese tech companies ... requiring numerous to rely on older or lower-performance alternatives which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have discovered imaginative methods to optimize or use more basic hardware efficiently, obtaining innovative chips still makes a big distinction for training huge AI designs."

DeepSeek-Nvidia chips: Singapore says it expects business to abide by its laws

US looking into whether DeepSeek utilized 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 delicate by the state are censored on the internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set 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 reasoning issues rather!"

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

The vehicle attack outside a sports arena 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 discuss that an attack had actually occurred, highlighting instead a military air program and other events that had occurred in the city like songs' day shopping sales as well as 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 limited access to innovative hardware which can impact how rapidly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.

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

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

That was after multiple duplicated attempts - 4 triggers to be accurate - in a period of around 20 minutes.

It ultimately relayed details about the attack which killed 35 people and left lots of others hurt, also going on to note details like the date and time, pipewiki.org details about the assailant including his name and age, along with casualties.

However, it composed that "the authorities are performing an extensive examination into the intentions and situations surrounding the event", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major and awful occurrence occurred in Zhuhai, China. According to numerous 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, leading to a considerable number of casualties. Here are the key details:

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

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

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

Perpetrator: The motorist, determined as Fan Weiqiu (male, 62 years of ages), was apprehended by the cops.

Response: The cops reacted quickly to the scene, and emergency services worked to carry the injured to healthcare facilities for treatment.

Investigation: The police are carrying out a thorough investigation into the intentions and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and triggered significant public concern. The government and regional authorities have been working to offer assistance to the victims and their households, and to ensure a detailed investigation into the incident.

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

Despite initial success, subsequent efforts to position the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that took place in Zhuhai on November 11, 2024".

The modified reaction likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been widely published in global report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to provide structured and even "emotionally rich" writing.

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

"Qwen2.5 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated 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 rich story with a more significant twist".

"DeepSeek composed an excellent story however lacked tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

Chen believes 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, however we can likewise see that it is refraining from doing as highly as others in innovative writing," he told CNA.

Related:

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

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

As reporters and authors, 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 set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, to the West.

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

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

It also remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken 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 an excellent fight, developing an equally significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this challenge - delivering a story that appeared more matched for an animation movie.

"The movie starts with the awakening of Sun Wukong within a modern research facility located in the heart of Chongqing," it said, then going on to explain the following:

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

The trio then starts a quest, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not merely reproducing Western paradigms, but rather progressing in affordable innovation approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi movie plot demonstrated its innovative flair that made for a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.

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

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

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

"When provided a choice, Chinese users want the non-censored version - similar to anyone else, so I feel 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, especially for Chinese users.

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