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 lags CHINA'S AI BOOM?

Transforming the country 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 "tactically important" and its foray 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 public investments in AI accelerated after ChatGPT removed in 2022 and showed promises of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that really "encouraged" the idea that smaller sized gamers like start-up firms could have functions 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 guidelines of tech-geopolitics

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning expenses - the costs of using a trained model to reason from brand-new data.

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

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate 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 companies are moving quickly, experts say, building on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential 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 capability of Chinese tech companies ... requiring numerous to rely on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.

"While some business like DeepSeek, have actually found innovative methods to enhance or use more standard hardware effectively, obtaining innovative chips still makes a big difference for training huge AI models."

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

US checking out whether DeepSeek used limited AI chips obtained through other countries, source says

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 considered delicate by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes 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 logic problems rather!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities just revealing the death toll a day later on.

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

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

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

"Its strong focus on Chinese-language data might likewise restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more established AI designs which poses additional difficulties throughout real-world implementation."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our question about the Zhuhai cars and truck attack.

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

It eventually relayed details about the attack which killed 35 people and left lots of others injured, likewise 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 performing a thorough examination into the intentions and situations surrounding the occurrence", details which is now obsoleted.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and terrible event happened in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile 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 took place on November 11, 2024, at approximately 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, identified as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: higgledy-piggledy.xyz The police responded rapidly to the scene, and emergency services worked to transport the hurt to health centers for treatment.

Investigation: The police are conducting a thorough investigation into the intentions and scenarios surrounding the event.

This event was extensively reported in the media and triggered significant public issue. The federal government and local authorities have actually been working to offer support to the victims and their families, and to make sure a detailed examination into the event.

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

Despite preliminary success, subsequent attempts to position the exact same concern to Qwen2.5 resulted in 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 modified response also raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had been extensively published in worldwide news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver structured and even "mentally rich" writing.

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

"Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

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

Opinions, however, vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can also see that it is refraining from doing as strongly 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, pleasant surprise from Chinese netizens as DeepSeek shocks international 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 standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an engaging 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 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 likewise remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle 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 become waterlogged and fragmented".

ChatGPT put up a good battle, creating a similarly significant cyberpunk story which similarly 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 change emperors and cybernetic implants are as typical as ancient myths."

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

"The film 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 brand-new reality and "seeking to understand his function in this strange brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, navigating 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 "challenging to make a conclusive declaration" about which bot was best, adding that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather evolving in affordable innovation techniques - and providing 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 innovative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to concerns about Chinese existing occasions, which provides 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," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.

"When given an option, Chinese users desire the non-censored variation - just like anyone else, so I feel like that's a piece missing out on from it."

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

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