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'S BEHIND 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 important" 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and showed guarantees of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller gamers like start-up firms could have roles to play in AI research and advancements, he adds.

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

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

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

2025 might also see the introduction of more Chinese AI designs dealing with innovative reasoning jobs.

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

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

Chinese AI companies are moving rapidly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to use generative AI to tasks and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a key hurdle for Chinese designers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech business ... requiring numerous to rely on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have actually found innovative methods to enhance or utilize more fundamental hardware effectively, obtaining advanced chips still makes a big difference for training large AI models."

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

US checking out whether DeepSeek utilized limited AI chips obtained through other countries, 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, subjects deemed sensitive 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 disputes or inform you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 question yet. Let's chat about math, coding, and reasoning problems instead!"

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

The car attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social media - with authorities only revealing the death toll a day later on.

DeepSeek failed to discuss that an attack had happened, highlighting instead a military air program and other occasions that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it may be a mix of aspects at play, bio.rogstecnologia.com.br such as censorship along with "a few useful 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 concentrate on Chinese-language data might also limit its adaptability (to carry out) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more recognized AI designs which poses extra obstacles during real-world release."

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

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

It eventually passed on details about the attack which killed 35 individuals and left dozens of others hurt, wiki.whenparked.com 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 composed that "the cops are carrying out an extensive investigation into the motives and situations surrounding the event", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and terrible occurrence happened in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) 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 event took place 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, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the authorities.

Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the hurt to medical facilities for treatment.

Investigation: The police are performing a comprehensive examination into the intentions and scenarios surrounding the occurrence.

This event was extensively reported in the media and triggered considerable public concern. The government and local authorities have actually been working to supply support to the victims and their households, and to make sure a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to posture the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on occasions that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been extensively published in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that develops gradually from curiosity to urgency, keeping the reader engaged. It provides an unexpected 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, mentally abundant story with a more considerable twist".

"DeepSeek wrote a great story but did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as highly as others in innovative writing," he told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks worldwide 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 standard sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an interesting storyline embeded in the year 2145 titled, "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 float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, 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 put up a good fight, developing a similarly dramatic cyberpunk story 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 change emperors and cybernetic implants are as typical as ancient misconceptions."

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

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

Realising his new truth and "seeking to understand his function in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not simply reproducing Western paradigms, however rather evolving in cost-efficient development methods - and delivering localised and enhanced outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate reactions to concerns about Chinese current events, which offers 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," noted Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When provided a choice, Chinese users want the non-censored variation - similar to anybody else, so I seem like that's a piece missing from it."

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

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