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 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 lags CHINA'S AI BOOM?

Transforming the nation 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 important" 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 financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed guarantees of real-world business applications, Chen told CNA.

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

The "focus on cost benefit" is a distinct function of Chinese AI, Chen states, with lower training and gratisafhalen.be reasoning expenses - the expenses of utilizing a trained model to reason from new data.

2025 could also see the development of more Chinese AI taking on innovative reasoning jobs.

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

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

Chinese AI business are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to use generative AI to tasks and establish advanced products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential 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 business ... requiring numerous to rely on older or lower-performance options which can slow training and reduce model capabilities," she said.

"While some business like DeepSeek, have actually discovered imaginative methods to optimize or use more basic hardware effectively, obtaining advanced chips still makes a big difference for training really big AI models."

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

US looking into whether DeepSeek used restricted AI chips obtained through other nations, 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 need 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 steer 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 further evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What took place in Zhuhai on November 11, 2024?"

The cars and truck 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 on.

DeepSeek failed to mention that an attack had actually taken location, highlighting instead a military air show and other events that had actually taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it might be a mix of aspects at play, such as censorship along with "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has limited access to advanced hardware which can impact how quickly and extensively the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may also restrict its flexibility (to bring out) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more recognized AI models which positions extra obstacles during real-world deployment."

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

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

It eventually relayed details about the attack which eliminated 35 people and left dozens 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 composed that "the authorities are carrying out a comprehensive investigation into the motives and scenarios surrounding the occurrence", details which is now obsoleted.

The driver, Fan, engel-und-waisen.de was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and tragic occurrence took place in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the key details:

Date and Time: The event happened on November 11, 2024, at around 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 of ages), was collared by the authorities.

Response: yewiki.org The authorities responded quickly to the scene, and emergency situation services worked to transfer the hurt to medical facilities for treatment.

Investigation: The authorities are performing a thorough investigation into the motives and scenarios surrounding the event.

This occasion was extensively reported in the media and triggered significant public issue. The federal government and local authorities have been working to supply assistance to the victims and their families, wavedream.wiki and to make sure a detailed examination into the event.

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

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

The transformed reaction also raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been extensively released in global news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that develops gradually from interest to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek wrote a good story however lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as highly 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 founder Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global AI scene

As journalists and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, 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 included elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle 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 end up being waterlogged and fragmented".

ChatGPT set up a good battle, creating a similarly dramatic cyberpunk story which likewise 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 story that seemed more fit for an animation film.

"The motion picture begins with the awakening of Sun Wukong within a high-tech 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 comprehend his function in this strange brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a definitive statement" 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 highlights how Chinese AI designs are not simply duplicating Western paradigms, but rather evolving in cost-effective development techniques - and delivering localised and enhanced outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual responses to questions about Chinese present events, which gives 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, founder and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored variation - just like anyone else, so I feel like that's a piece missing from it."

Independent Beijing-based expert 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 topics. They're utilizing it for other efficient methods," Chen said.