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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

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

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the idea that smaller gamers like start-up firms could have functions to play in AI research study and developments, he includes.

'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 simply changed the rules of tech-geopolitics

The "focus on cost advantage" is an unique function of Chinese AI, Chen says, with lower training and inference costs - the costs of using a trained design to draw conclusions from new information.

2025 could likewise see the development of more Chinese AI models tackling advanced thinking tasks.

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

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

Chinese AI business are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to jobs and develop advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key obstacle 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) limit the ability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and lower design capabilities," she said.

"While some business like DeepSeek, have actually found innovative methods to optimize or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a huge 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 countries, 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 internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about mathematics, coding, and logic problems rather!"

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

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

DeepSeek failed to discuss that an attack had actually occurred, highlighting instead a military air program and other occasions that had actually occurred in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it may be a mix of elements at play, such as censorship as well as "a few practical constraints".

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

"Its strong focus on Chinese-language data may also limit its adaptability (to carry out) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been checked as broadly or on the same scale as more recognized AI models which postures additional obstacles throughout real-world release."

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

That sought numerous duplicated efforts - four triggers to be exact - in a period of around 20 minutes.

It ultimately relayed details about the attack which killed 35 individuals and left dozens of others hurt, likewise going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the authorities are carrying out a thorough examination into the intentions and situations surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a significant and awful incident occurred in Zhuhai, China. According to several news sources, a guy 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 occurred 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 driver, determined as Fan Weiqiu (male, 62 years old), was captured by the police.

Response: The cops responded rapidly to the scene, and emergency situation services worked to carry the hurt to healthcare facilities for treatment.

Investigation: The authorities are performing a comprehensive examination into the intentions and circumstances surrounding the incident.

This occasion was widely reported in the media and triggered significant public concern. The federal government and local authorities have actually been working to offer assistance to the victims and their families, and to ensure a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent attempts to present the exact same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been extensively released in global report 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 even "mentally rich" writing.

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

"Qwen2.5 delivered a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, though, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as highly as others in innovative writing," he informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

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

As 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 embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, yewiki.org Journey to the West.

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

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

It also remarkably reimagined standard heroes Sun Wukong as "an ironical, 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 "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a great battle, developing a similarly remarkable cyberpunk storyline 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 common as ancient misconceptions."

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

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

Realising his brand-new reality and "looking for to comprehend his purpose in this weird new world", he then escapes and fulfills 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 under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a definitive 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 highlights how Chinese AI designs are not just duplicating Western paradigms, but rather evolving in cost-effective development approaches - and providing localised and improved results.

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 produced a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to questions about Chinese current occasions, which offers it an included advantage.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

"When provided an option, Chinese users desire the non-censored version - similar to anybody else, so I feel like that's a piece missing out on from it."

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.

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