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'S BEHIND 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 essential" and its venture into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Policy Institute's Center for China Analysis.

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

But it was DeepSeek's increase that truly "encouraged" the idea that smaller sized players like start-up firms could have roles to play in AI research study and developments, he includes.

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

Commentary: DeepSeek - how a Chinese AI company simply altered the rules of tech-geopolitics

The "emphasis on expense advantage" is a distinctive feature of Chinese AI, Chen says, with lower training and inference costs - the expenses of using a trained model to reason from brand-new data.

2025 might likewise see the introduction of more Chinese AI designs taking on innovative reasoning jobs.

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

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

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

But on the other side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial obstacle for Chinese designers, noted 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 many to depend on older or lower-performance alternatives which can slow training and reduce design abilities," she said.

"While some business like DeepSeek, have actually discovered innovative ways to enhance or use more basic hardware efficiently, obtaining innovative chips still makes a huge distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates companies to abide by its laws

US checking out whether DeepSeek utilized restricted AI chips obtained through other countries, source says

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 internet so it should 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 programmed to avoid 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 issues instead!"

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

The car attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only disclosing the death toll a day later.

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

Dr Zhang believes that it might be a mix of elements at play, such as censorship as well as "a few practical constraints".

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

"Its strong concentrate on Chinese-language data may also limit its adaptability (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the very same scale as more established AI models which positions additional difficulties throughout real-world deployment."

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

That wanted multiple duplicated attempts - four triggers to be exact - in a period of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 individuals and left lots of others hurt, 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 wrote that "the cops are carrying out an extensive examination into the motives and circumstances surrounding the incident", details which is now dated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major and terrible incident took place in Zhuhai, China. According to several 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 crucial details:

Date and Time: The occurrence occurred 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 motorist, identified as Fan Weiqiu (male, 62 years old), was collared by the police.

Response: pediascape.science The police reacted rapidly to the scene, and emergency services worked to transfer the injured to healthcare facilities for treatment.

Investigation: The police are conducting an extensive investigation into the motives and situations surrounding the event.

This occasion was widely reported in the media and caused considerable public issue. The federal government and local authorities have actually been working to offer support to the victims and their households, and to make sure a detailed investigation into the event.

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

Despite initial success, subsequent efforts to position the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on events that occurred in Zhuhai on November 11, 2024".

The modified action likewise raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had been widely 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 deliver structured and even "mentally rich" writing.

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

"Qwen2.5 delivered a story that builds gradually from interest to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more substantial twist".

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

Opinions, however, vary.

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

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

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts 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 motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, yewiki.org Journey to the West.

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

It consisted of 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 also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a great fight, creating a similarly significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 misconceptions."

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

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

Realising his brand-new reality and "looking for to understand his function in this strange brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely reproducing Western paradigms, however rather evolving in economical development methods - and delivering localised and improved results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate reactions to concerns about Chinese present occasions, which provides it an included advantage.

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

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

"When provided an option, Chinese users want the non-censored variation - much like anybody 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, hb9lc.org specifically for Chinese users.

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