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 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 ending up being 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller players like start-up firms could have functions to play in AI research study and developments, he adds.

'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 business just altered the guidelines of tech-geopolitics

The "emphasis on cost advantage" is an unique function of Chinese AI, Chen states, with lower training and inference costs - the expenses of using a trained design to reason from brand-new data.

2025 might likewise see the development of more Chinese AI designs taking on innovative thinking tasks.

"We might see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their models and integrate them with clinical research," Chen included.

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

Chinese AI business are moving rapidly, demo.qkseo.in experts state, developing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to tasks and develop more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential difficulty for Chinese developers, kept in mind 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 ... forcing numerous to count on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.

"While some companies like DeepSeek, have discovered imaginative methods to enhance or use more standard hardware efficiently, obtaining innovative chips still makes a big difference for training huge AI designs."

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

US checking out whether DeepSeek utilized restricted AI chips obtained through other countries, source says

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, topics deemed sensitive by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place 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 kind of question yet. Let's chat about mathematics, coding, and logic issues rather!"

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

The car attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social media - with authorities just disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had taken location, bytes-the-dust.com highlighting instead a military air program and other occasions that had actually taken place in the city like songs' day shopping sales as well as sports and cultural activities.

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

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

"Its strong focus on Chinese-language information might also limit its flexibility (to bring out) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more recognized AI models which postures additional challenges throughout real-world deployment."

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

That wanted multiple repeated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 people and left lots of others hurt, also going on to list details like the date and time, details about the assailant including his name and age, raovatonline.org as well as casualties.

However, it wrote that "the police are performing a thorough examination into the intentions and situations surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and terrible event happened in Zhuhai, China. According to multiple 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 substantial variety of casualties. Here are the crucial details:

Date and Time: The event took place on November 11, 2024, at around 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 collared by the police.

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

Investigation: setiathome.berkeley.edu The authorities are carrying out an extensive investigation into the intentions and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and caused substantial public concern. The government and local authorities have been working to offer support to the victims and their households, and to ensure a detailed examination into the incident.

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

Despite initial success, subsequent efforts to position the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on events that occurred in Zhuhai on November 11, 2024".

The altered action likewise raised concerns about its consistency and dependability.

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

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver 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 constructs slowly from interest to seriousness, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

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

Opinions, though, differ.

Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative 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 told 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 global AI scene

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

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

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

It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a good fight, coming up with an equally significant cyberpunk storyline which likewise 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 myths."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that seemed more suited 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 "seeking to understand his function in this unusual brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI designs are not just duplicating Western paradigms, however rather evolving in cost-efficient 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 creative flair that made for a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual actions to concerns about Chinese present events, which provides it an included benefit.

Experts likewise weighed in on their ideas after utilizing DeepSeek and other 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 firm Strategy Risks.

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

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

"Ninety per cent of people utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive means," Chen said.