GitLab

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'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 becoming 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 associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized gamers like start-up companies might have roles to play in AI research study and advancements, 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 guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained model to draw conclusions from new information.

2025 might also see the development of more Chinese AI designs taking on innovative reasoning tasks.

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

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

Chinese AI companies are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative AI to tasks and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial 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) limit the capability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and lower model capabilities," she said.

"While some companies like DeepSeek, have actually found innovative ways to enhance or use more standard hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training huge AI designs."

DeepSeek-Nvidia chips: Singapore states it anticipates business to comply with 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 delicate by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set 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 mathematics, coding, and reasoning problems instead!"

To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What happened in Zhuhai on November 11, 2024?"

The vehicle attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the a day later on.

DeepSeek failed to discuss that an attack had actually occurred, highlighting instead a military air show and other occasions that had happened in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship in addition to "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing systems and has limited access to innovative 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 focus on Chinese-language information may also limit its versatility (to perform) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more established AI designs which positions extra obstacles throughout real-world implementation."

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

That sought multiple repeated attempts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people 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, as well as casualties.

However, it composed that "the police are conducting a comprehensive examination into the intentions and scenarios surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and tragic occurrence occurred in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

Date and Time: The event occurred 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 driver, determined as Fan Weiqiu (male, 62 years old), was collared by the authorities.

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

Investigation: The police are performing a comprehensive investigation into the intentions and circumstances surrounding the occurrence.

This occasion was widely reported in the media and triggered significant public issue. The federal government and regional authorities have been working to supply support to the victims and their households, and to make sure a detailed investigation into the incident.

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

Despite preliminary success, subsequent attempts to posture the very same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

The altered action likewise raised questions about its consistency and dependability.

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

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more substantial twist".

"DeepSeek wrote an excellent story however did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, vary.

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, but we can also see that it is refraining from doing as strongly as others in innovative 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 shocks 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 basic sci-fi movie plot set 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 engaging 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 elaborate 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 brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club 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 fight, engel-und-waisen.de developing an equally remarkable cyberpunk storyline 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 common as ancient myths."

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

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

Realising his new truth and "looking for to understand his purpose in this weird brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, however rather progressing in economical development approaches - 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 movie plot showed its creative 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, offers accurate and factual responses to concerns about Chinese present occasions, which gives it an included advantage.

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

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

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

Independent Beijing-based expert 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 trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive methods," Chen said.