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 startup 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 nation into a tech superpower has 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 crucial" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated 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 guarantees of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that really "encouraged" the idea that smaller sized gamers like start-up companies could have roles to play in AI research study and advancements, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply changed the guidelines of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses - the expenses of using a trained design to draw conclusions from new information.

2025 might also see the introduction of more Chinese AI designs dealing with advanced thinking tasks.

"We could see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with scientific research," Chen added.

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

Chinese AI business are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key hurdle for Chinese designers, 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 ability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and decrease model capabilities," she said.

"While some business like DeepSeek, have actually found creative ways to enhance or utilize more fundamental hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws

US checking out whether DeepSeek utilized restricted AI chips obtained through other countries, 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 disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to guide clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and logic issues instead!"

To even more evaluate 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 automobile attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the death toll a day later.

DeepSeek failed to point out that an attack had happened, highlighting instead a military air program and other events that had happened in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship along with "a couple of useful constraints".

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

"Its strong focus on Chinese-language data may likewise limit its adaptability (to perform) multilingual jobs ... As a fairly new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more recognized AI designs which positions additional difficulties 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 eventually communicated 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, along with casualties.

However, it wrote that "the police are performing an extensive examination into the motives and situations surrounding the incident", details which is now obsoleted.

The motorist, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and awful occurrence occurred in Zhuhai, China. According to multiple news sources, a man 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 key details:

Date and Time: The occurrence took place on November 11, 2024, at roughly 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 chauffeur, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The authorities reacted rapidly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: garagesale.es The cops are performing a thorough examination into the intentions and situations surrounding the incident.

This event was widely reported in the media and triggered considerable public issue. The federal government and local authorities have been working to provide support to the victims and their households, and to guarantee a detailed investigation into the occurrence.

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

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

The transformed response also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been commonly released in worldwide 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 provide structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that develops slowly from curiosity to urgency, 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, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".

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

Opinions, however, vary.

Chen thinks 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 highly 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, enjoyable surprise from Chinese netizens as DeepSeek shocks global AI scene

As reporters and writers, 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 embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.

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

It included intricate 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 combat 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 an excellent battle, developing an equally remarkable storyline which similarly 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 - providing a story that seemed more fit for an animation film.

"The motion picture starts with the awakening of Sun Wukong within a high-tech research facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "seeking to comprehend his purpose in this strange brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard 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 information and hardware optimization".

Her insight highlights how Chinese AI models are not simply duplicating Western paradigms, however rather developing in cost-effective development techniques - and providing localised and improved outcomes.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to questions about Chinese existing occasions, which gives it an added benefit.

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

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

"When offered an option, Chinese users want the non-censored version - much like anyone 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 attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive ways," Chen said.