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 nation into a tech superpower has actually long been President Xi Jinping's objective and demo.qkseo.in 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 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 accelerated after ChatGPT removed in 2022 and showed guarantees of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that really "encouraged" the idea that smaller sized gamers 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 company DeepSeek's AI model as impactful as it claims?

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

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

2025 could likewise see the development of more Chinese AI designs dealing with innovative reasoning tasks.

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

AGI refers to a system with intelligence on par with human abilities.

Chinese AI business are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to tasks and establish advanced 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 designers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech business ... requiring many to count on older or lower-performance options which can slow training and minimize design abilities," she said.

"While some companies like DeepSeek, have actually found creative ways to optimize or utilize more standard hardware effectively, obtaining innovative chips still makes a big distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to comply with its laws

US looking into 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, subjects 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 occurred 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 type of concern yet. Let's chat about mathematics, coding, and reasoning problems instead!"

To further test 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 stadium in the southern Chinese city was at first 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 happened, highlighting instead a military air program and other occasions that had actually occurred 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 elements 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 innovative hardware which can affect how quickly and thoroughly the model can be trained or updated," she said, forum.pinoo.com.tr indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also limit its flexibility (to bring out) multilingual jobs ... 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 additional obstacles during real-world release."

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

That sought multiple repeated attempts - 4 triggers to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which eliminated 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, along with casualties.

However, it composed that "the authorities are carrying out a thorough examination into the intentions and situations surrounding the incident", details which is now outdated.

The driver, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: larsaluarna.se On Nov 11, 2024, a major and tragic occurrence happened in Zhuhai, China. According to numerous news sources, setiathome.berkeley.edu a male named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the essential 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: systemcheck-wiki.de The attack led to 35 deaths and 43 injuries.

Perpetrator: The motorist, recognized as Fan Weiqiu (male, bytes-the-dust.com 62 years old), was apprehended by the police.

Response: The police reacted quickly to the scene, and emergency services worked to transport the hurt to healthcare facilities for treatment.

Investigation: The police are carrying out a comprehensive investigation into the intentions and scenarios surrounding the event.

This occasion was commonly reported in the media and caused significant public issue. The federal government and regional authorities have actually been working to supply assistance to the victims and their families, and to make sure a detailed examination into the event.

If you need more detailed details or have specific concerns about the incident, feel free to ask.

Despite initial success, subsequent efforts to pose 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 occurred 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 extensively released in worldwide report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to deliver structured and even "emotionally abundant" writing.

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

"Qwen2.5 provided a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It uses an unexpected 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 good story however did not have stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, 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 founder Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international 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 set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

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

It consisted of elaborate 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 likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", as a cyborg bar 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 put up a good battle, coming up with an equally remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary 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 obstacle - providing a story that appeared more fit for an animation film.

"The motion picture begins with the awakening of Sun Wukong within a modern research center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "looking for to understand his function in this weird brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a conclusive statement" about which bot was best, systemcheck-wiki.de adding that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, however rather evolving in affordable development methods - and providing localised and improved outcomes.

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

DeepSeek's sci-fi film plot showed its creative flair that made for a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate responses to questions about Chinese current events, which offers it an added advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.

"When offered a choice, Chinese users desire the non-censored version - much like anyone else, so I seem like that's a piece missing out on from it."

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