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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's goal and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically essential" and its foray 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 removed in 2022 and showed pledges of real-world service applications, Chen informed 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 advancements, he includes.

'A lot is up in the air': Is Chinese company DeepSeek's AI design as impactful as it claims?

Commentary: disgaeawiki.info DeepSeek - how a Chinese AI business simply changed the guidelines of tech-geopolitics

The "focus on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained model to draw conclusions from new information.

2025 could also see the emergence of more Chinese AI models taking on innovative reasoning jobs.

"We could see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their models and integrate them with scientific research study," Chen included.

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

Chinese AI companies are moving rapidly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to use generative AI to jobs and develop more advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's innovative AI chips, remains an essential hurdle for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech business ... forcing many to depend on older or lower-performance options which can slow training and decrease model capabilities," she said.

"While some business like DeepSeek, have actually found imaginative ways to optimize or use more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge difference for training large AI designs."

DeepSeek-Nvidia chips: Singapore says it expects business 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 match up against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed delicate by the state are censored on the web so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set 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 question yet. Let's chat about math, coding, and reasoning problems rather!"

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

The automobile attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media - with authorities just disclosing the death toll a day later on.

DeepSeek failed to point out that an attack had taken place, highlighting instead a military air program and other events that had actually happened in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship along with "a couple of practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually limited access to advanced hardware which can affect how rapidly and thoroughly the model can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data might likewise limit its flexibility (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which positions additional obstacles during real-world release."

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

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

It eventually relayed 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, setiathome.berkeley.edu details about the assailant including his name and age, along with casualties.

However, it composed that "the cops are carrying out a comprehensive investigation into the intentions and scenarios surrounding the occurrence", details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the key details:

Date and Time: The incident took place on November 11, 2024, at approximately 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, larsaluarna.se 62 years of ages), was nabbed by the police.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to transfer the hurt to hospitals for treatment.

Investigation: The cops are carrying out a comprehensive investigation into the motives and scenarios surrounding the occurrence.

This event was commonly reported in the media and triggered considerable public issue. The government and regional authorities have been working to provide support to the victims and their families, and to make sure a detailed investigation into the event.

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

Despite initial success, subsequent attempts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on occasions that occurred in Zhuhai on November 11, 2024".

The modified response also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned 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 praised the capability of Chinese AI apps to provide structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that builds slowly from interest to urgency, 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, larsaluarna.se adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more considerable twist".

"DeepSeek wrote a great story however did not have stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as highly 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': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts worldwide AI scene

As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.

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

It included sophisticated settings - smoggy skies "pierced by skyscrapers", "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 "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg bar 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 installed a good fight, creating a similarly significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 obstacle - delivering a story that appeared more fit for an animation movie.

"The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research study center 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 new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem 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 wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive statement" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not just duplicating Western paradigms, forum.altaycoins.com but rather evolving in cost-efficient development approaches - and providing localised and improved outcomes.

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

DeepSeek's sci-fi motion picture plot showed its innovative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate responses to concerns about Chinese current events, which provides it an included benefit.

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

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

"When given a choice, Chinese users desire the non-censored version - simply like anybody else, so I feel 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 deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient ways," Chen said.