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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated researcher 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 business applications, Chen informed CNA.

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

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

Commentary: DeepSeek - how a Chinese AI company just altered the guidelines of tech-geopolitics

The "focus on cost advantage" 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 brand-new information.

2025 could also see the emergence of more Chinese AI designs tackling sophisticated thinking tasks.

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

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

Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and wiki.whenparked.com establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial obstacle for Chinese developers, 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 options which can slow training and decrease model abilities," she said.

"While some business like DeepSeek, have found creative methods to optimize or utilize more standard hardware efficiently, obtaining advanced chips still makes a big distinction for training extremely big AI designs."

DeepSeek-Nvidia chips: Singapore says it expects companies to adhere to its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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, subjects deemed delicate by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what occurred 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 type of question yet. Let's chat about mathematics, coding, and logic issues rather!"

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

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

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

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

"DeepSeek relies on a mix of older graphics processing units and has limited access to cutting-edge hardware which can impact 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 information might likewise restrict its flexibility (to carry out) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more recognized AI designs which poses extra obstacles during real-world deployment."

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

That was after numerous duplicated efforts - 4 prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 people and left lots of others injured, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the authorities are performing a comprehensive examination into the motives and scenarios surrounding the event", details which is now dated.

The driver, Fan, was performed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and awful event took place in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) 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 incident occurred 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 chauffeur, identified as Fan Weiqiu (male, 62 years old), was captured by the cops.

Response: The police responded quickly to the scene, and emergency situation services worked to transport the injured to hospitals for treatment.

Investigation: The cops are carrying out a thorough investigation into the intentions and situations surrounding the event.

This occasion was extensively reported in the media and caused substantial public concern. The government and local authorities have been working to supply assistance to the victims and their families, setiathome.berkeley.edu and to guarantee a detailed investigation into the occurrence.

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

Despite initial success, subsequent attempts to present the exact same concern to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had actually been commonly published in worldwide news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability 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 writer Amanda Caswell, who specialises in AI.

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

"DeepSeek wrote an excellent story however lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, vary.

Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative 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 imaginative 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 writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic 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 came up with an appealing story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

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

It likewise brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg club 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 set up a good fight, developing a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 myths."

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

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

Realising his new reality and "seeking to comprehend his purpose in this weird new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive declaration" about which bot was best, including that each showed 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, however rather progressing in economical development methods - and providing localised and improved 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 innovative flair that produced a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, higgledy-piggledy.xyz provides precise and accurate reactions to concerns about Chinese existing occasions, which gives 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," noted Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When given an option, Chinese users want the non-censored variation - much like anybody else, so I seem 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, particularly for Chinese users.

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