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 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 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 "strategically essential" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated scientist at the Asia Society Policy Institute's Center for wiki.snooze-hotelsoftware.de China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed guarantees of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller sized players like start-up firms could have roles to play in AI research 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 changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the expenses of utilizing a trained model to draw conclusions from new data.

2025 could likewise see the emergence of more Chinese AI designs tackling innovative reasoning tasks.

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

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

Chinese AI business are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial difficulty 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) restrict the capability of Chinese tech business ... requiring lots of to count on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have discovered innovative ways to optimize or use more standard hardware efficiently, obtaining advanced chips still makes a huge difference for training huge AI designs."

DeepSeek-Nvidia chips: yewiki.org Singapore states it expects companies to abide by its laws

US checking out 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 conflicts or tell you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to avoid 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 mathematics, coding, and logic issues rather!"

To further test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred in Zhuhai on November 11, 2024?"

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

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

Dr Zhang believes that it may be a mix of elements at play, such as censorship in addition to "a couple of useful constraints".

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

"Its strong concentrate on Chinese-language data may also restrict its versatility (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more established AI models which postures additional obstacles during real-world implementation."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly answered our question about the Zhuhai cars and truck attack.

That wanted multiple repeated attempts - four prompts to be accurate - in a period of around 20 minutes.

It ultimately relayed details about the attack which killed 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, in addition to casualties.

However, it wrote that "the police are conducting a comprehensive examination into the intentions and circumstances surrounding the event", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, forum.batman.gainedge.org a significant and awful incident took place in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the crucial 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 led to 35 deaths and 43 injuries.

Perpetrator: The motorist, determined as (male, 62 years of ages), was captured by the police.

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

Investigation: The cops are performing a comprehensive examination into the motives and wiki.snooze-hotelsoftware.de circumstances surrounding the incident.

This event was extensively reported in the media and caused significant public issue. The government and regional authorities have been working to offer support to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

Despite preliminary success, subsequent attempts to present the very same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT cited public details that had actually been extensively released in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 used a story with a more reflective tone and smoother emotional transitions for a well-paced story," wrote 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 provides an unexpected and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more substantial twist".

"DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, differ.

Chen thinks 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 tasks, but we can also 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 founder Liang Wenfeng?

'Made in China': it-viking.ch Pride, pleasant surprise from Chinese netizens as DeepSeek shocks worldwide AI scene

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

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

It included sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

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

ChatGPT set up a good battle, coming up with a similarly remarkable 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 change emperors and cybernetic implants are as common as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that appeared more matched for an animation movie.

"The movie 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 brand-new reality and "seeking to comprehend his purpose in this odd new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, but rather evolving in economical innovation techniques - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi film 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 precise and accurate responses to concerns about Chinese present occasions, which gives it an added advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and forum.altaycoins.com CEO of the research firm Strategy Risks.

"When given an option, Chinese users desire the non-censored variation - similar to 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, particularly for Chinese users.

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