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 generated 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 important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated 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 showed pledges of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the idea that smaller sized players like start-up companies could have roles to play in AI research study and developments, 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 expense benefit" is an unique function of Chinese AI, Chen states, with lower training and reasoning costs - the costs of using a trained model to draw conclusions from brand-new data.

2025 could likewise see the emergence of more Chinese AI models tackling innovative reasoning jobs.

"We might see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others focus 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 abilities.

Chinese AI companies are moving rapidly, larsaluarna.se analysts state, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains an essential difficulty for Chinese developers, kept in mind Dr Marina Zhang, wiki.snooze-hotelsoftware.de an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the capability of Chinese tech companies ... requiring many 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 creative methods to enhance or utilize more standard hardware effectively, obtaining advanced chips still makes a big distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates business to comply with its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, 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 considered delicate by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed 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 concern yet. Let's chat about mathematics, coding, and reasoning problems instead!"

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

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

DeepSeek failed to point out that an attack had taken place, highlighting instead a military air program and other occasions 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 along with "a few useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to advanced hardware which can impact how quickly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise restrict its flexibility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI designs which presents additional obstacles throughout real-world implementation."

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

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

It ultimately communicated about the attack which killed 35 people and left lots of others hurt, 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 wrote that "the authorities are conducting a thorough investigation into the motives and situations surrounding the event", wiki.dulovic.tech details which is now obsoleted.

The motorist, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and awful event occurred in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the crucial details:

Date and Time: The event happened on November 11, 2024, at roughly 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 motorist, determined as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The authorities responded rapidly to the scene, and emergency situation services worked to transport the hurt to health centers for treatment.

Investigation: The cops are performing an extensive examination into the intentions and scenarios surrounding the event.

This occasion was widely reported in the media and triggered considerable public concern. The government and regional authorities have actually been working to supply assistance to the victims and their households, and to make sure a detailed examination into the incident.

If you require more detailed details or have specific concerns about the occurrence, do not hesitate to ask.

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

The modified action also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited public details that had been extensively published in international 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 deliver structured and even "emotionally abundant" writing.

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

"Qwen2.5 provided a story that develops gradually from curiosity to urgency, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more substantial twist".

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

Opinions, though, differ.

Chen thinks 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, 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 creator wiki.snooze-hotelsoftware.de Liang Wenfeng?

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

As journalists and authors, we had 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 classic Chinese folklore legendary, Journey to the West.

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

It consisted of intricate 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 also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat 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 become waterlogged and fragmented".

ChatGPT set up an excellent fight, developing an equally dramatic 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 typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this challenge - providing a storyline that appeared more fit for an animation film.

"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 truth and "seeking to comprehend his function in this weird brand-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 quest, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive declaration" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not merely replicating Western paradigms, but rather progressing in economical innovation approaches - and delivering localised and enhanced results.

In our tests, each bot showcased their own distinct strengths, forum.altaycoins.com which certainly made direct contrasts challenging.

DeepSeek's sci-fi motion picture plot showed its imaginative 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, offers precise and factual responses to concerns about Chinese current occasions, which provides it an added benefit.

Experts likewise weighed in on their thoughts 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, founder and CEO of the research study firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - just like anyone 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 bytes-the-dust.com Chinese users.

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