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 lags 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 "strategically essential" and its foray into the field has actually 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 financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller players like start-up companies might have functions to play in AI research and developments, 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 just altered the guidelines of tech-geopolitics

The "emphasis on cost advantage" is an unique feature of Chinese AI, Chen says, with lower training and - the costs of utilizing a trained model to draw conclusions from new data.

2025 could also see the development of more Chinese AI models dealing with sophisticated reasoning tasks.

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

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

Chinese AI business are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to apply generative AI to jobs and develop more sophisticated products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key 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 ability of Chinese tech companies ... requiring many to count on older or lower-performance options which can slow training and minimize design abilities," she said.

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

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

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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, archmageriseswiki.com subjects considered delicate by the state are censored on the web so it need to come as no 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 configured to stay away from 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 mathematics, coding, and reasoning issues rather!"

To even more test for accuracy and wiki.asexuality.org self-censorship, pediascape.science we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What took place in Zhuhai on November 11, 2024?"

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

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

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

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to innovative hardware which can affect how rapidly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might likewise limit its versatility (to bring out) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more recognized AI models which poses additional challenges during real-world implementation."

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

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

It ultimately communicated details about the attack which eliminated 35 people and left lots of others injured, 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 cops are conducting an extensive examination into the motives and circumstances surrounding the event", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and awful event happened in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

Date and Time: The occurrence happened 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The authorities reacted quickly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The cops are conducting a comprehensive examination into the intentions and scenarios surrounding the event.

This event was commonly reported in the media and caused significant public concern. The federal government and regional authorities have actually been working to offer support to the victims and their households, and to guarantee a detailed examination into the incident.

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

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

The transformed action likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been commonly published in worldwide news reports 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 deliver structured and pediascape.science even "emotionally rich" writing.

"DeepSeek-R1 offered 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 delivered a story that constructs gradually from interest to seriousness, 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, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more significant twist".

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

Opinions, however, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise 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 creator Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international AI scene

As reporters and authors, we needed 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, including main characters from the classic Chinese folklore epic, Journey to the West.

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

It consisted of sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed a great battle, creating an equally remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as typical as ancient myths."

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

"The movie begins with the awakening of Sun Wukong within a high-tech research 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 function in this strange new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive statement" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not merely replicating Western paradigms, but rather evolving in affordable innovation approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi film plot showed its creative flair that produced a more engaging 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 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, creator and CEO of the research firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored version - similar to anyone else, so I seem 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, specifically for Chinese users.

"Ninety per cent of individuals using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient methods," Chen said.