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 startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually 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 "tactically essential" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller sized players like start-up companies might have roles to play in AI research study and advancements, he adds.

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

Commentary: hb9lc.org DeepSeek - how a Chinese AI business simply altered the guidelines of tech-geopolitics

The "emphasis on cost benefit" is an unique feature of Chinese AI, Chen says, with lower training and reasoning costs - the costs of utilizing a trained design to draw conclusions from brand-new information.

2025 could also see the development of more Chinese AI models dealing with advanced thinking tasks.

"We could see some AI companies focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with clinical research," Chen included.

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

Chinese AI business are moving rapidly, experts say, building on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and develop advanced products beyond chatbots.

But on the other hand, it-viking.ch access to high-end hardware, especially Nvidia's innovative AI chips, remains a key hurdle 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 capability of Chinese tech business ... forcing many to depend on older or lower-performance options which can slow training and reduce model abilities," she said.

"While some business like DeepSeek, have found creative methods to optimize or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge difference for training huge AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to abide by 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, topics deemed sensitive by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests suggest 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 concern yet. Let's chat about math, coding, and reasoning problems rather!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: "What happened 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 networks - with authorities just revealing the death toll a day later on.

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

Dr Zhang thinks that it might be a mix of factors at play, such as censorship in addition to "a few useful constraints".

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

"Its strong concentrate on Chinese-language information may likewise limit its adaptability (to bring out) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more recognized AI models which postures extra challenges during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our concern about the Zhuhai cars and truck attack.

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

It eventually communicated details about the attack which eliminated 35 individuals and left dozens of others injured, likewise 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 carrying out a thorough examination into the motives and circumstances surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and awful occurrence happened in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential 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 driver, as Fan Weiqiu (male, 62 years old), was collared by the cops.

Response: The police responded quickly to the scene, and emergency situation services worked to carry the hurt to health centers for treatment.

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

This occasion was extensively reported in the media and caused considerable public concern. The government and local authorities have actually been working to offer support to the victims and their families, and to make sure a detailed investigation into the occurrence.

If you need more detailed details or have specific concerns about the occurrence, feel totally free to ask.

Despite preliminary success, subsequent efforts to pose the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that occurred in Zhuhai on November 11, 2024".

The modified response also raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had actually been extensively published in international report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to provide structured and even "mentally rich" writing.

"DeepSeek-R1 offered a story with a more reflective tone and smoother psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops slowly from interest to seriousness, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more substantial twist".

"DeepSeek composed a great story but lacked tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed 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 jolts global AI scene

As reporters and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

It included 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 remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen 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 installed a good battle, coming up with an equally significant 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 replace emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his brand-new reality and "seeking to understand his function in this unusual new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a conclusive statement" about which bot was best, adding that each displayed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not just replicating Western paradigms, but rather developing in economical innovation approaches - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot showed its imaginative 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 factual actions to questions about Chinese existing events, which provides it an added 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 study company Strategy Risks.

"When offered an option, Chinese users want the non-censored version - just like anybody else, so I feel like that's a piece missing 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 attempting to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive methods," Chen said.