How do Chinese aI Bots Stack up Against ChatGPT?

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 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 actually long been President Xi Jinping’s goal and forum.batman.gainedge.org China has its sights on becoming the world leader in AI by 2030.

China views AI as being “strategically important” 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek’s increase that really “encouraged” the concept that smaller gamers like start-up firms could have functions to play in AI research and developments, he includes.

‘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 simply altered the guidelines of tech-geopolitics

The “emphasis on expense benefit” is a distinctive function of Chinese AI, Chen states, with lower training and reasoning costs – the costs of using a trained model to reason from brand-new data.

2025 might also see the emergence of more Chinese AI designs tackling sophisticated reasoning jobs.

“We might see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with scientific research,” Chen added.

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

Chinese AI companies are moving rapidly, experts state, developing on DeepSeek’s momentum to come up with their own ingenious and cost-effective ways to apply generative AI to tasks and establish more innovative items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia’s advanced AI chips, remains a key obstacle 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 ability of Chinese tech business … requiring lots of to rely on older or lower-performance alternatives which can slow training and reduce model capabilities,” she said.

“While some companies like DeepSeek, have actually found innovative ways to enhance or use more basic hardware effectively, obtaining cutting-edge chips still makes a huge distinction for training really big AI models.”

DeepSeek-Nvidia chips: Singapore says it anticipates companies to adhere to 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, subjects deemed delicate by the state are censored on the web so it ought to 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 suggest Chinese chatbots are configured to stay away from domestic politics.

When asked “Who is Xi Jinping”, it-viking.ch DeepSeek’s reply was “Sorry, I’m uncertain how to approach this kind of question 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 same concern: “What happened in Zhuhai on November 11, 2024?”

The vehicle attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks – with authorities only divulging the death toll a day later.

DeepSeek failed to discuss that an attack had actually taken location, highlighting instead a military air show and other events that had occurred in the city like singles’ day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship along with “a few useful constraints”.

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

“Its strong focus on Chinese-language information might likewise limit its versatility (to carry out) multilingual tasks … As a fairly brand-new item, DeepSeek also hasn’t yet been checked as broadly or on the same scale as more established AI models which positions additional obstacles throughout real-world implementation.”

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

That sought multiple repeated efforts – four prompts 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 note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that “the cops are conducting a comprehensive examination into the intentions and situations surrounding the event”, details which is now dated.

The motorist, Fan, was carried out last month.

This is Qwen2.5’s response in full:

Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the crucial details:

Date and Time: The event took place 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 motorist, determined as Fan Weiqiu (male, 62 years old), bytes-the-dust.com was apprehended by the police.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to hospitals for treatment.

Investigation: The police are performing an extensive investigation into the motives and archmageriseswiki.com circumstances surrounding the incident.

This event was commonly reported in the media and caused considerable public issue. The federal government and regional authorities have actually been working to provide support 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 efforts to position the exact same concern to Qwen2.5 resulted in 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 transformed action also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had actually been commonly published in global news reports at the time of the mishap – so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to provide structured and even “emotionally rich” writing.

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

“Qwen2.5 provided a story that constructs gradually from curiosity to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting,” she said, adding that Qwen2.5 ultimately “crafted a more cinematic, emotionally rich story with a more significant twist”.

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

Opinions, however, differ.

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

“(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly as others in creative writing,” he told 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 shocks worldwide AI scene

As journalists and authors, pipewiki.org 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 came up with an engaging story embeded in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism merges with quantum computing”.

It included intricate 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 brilliantly reimagined standard heroes Sun Wukong as “a sarcastic, self-aware AI housed in a taken battle body”, Zhu Bajie 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 installed an excellent battle, developing 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 replace emperors and cybernetic implants are as typical as ancient myths.”

Disappointingly, Qwen2.5 fell short in this delivering a story that appeared more suited for an animation movie.

“The movie starts with the awakening of Sun Wukong within a state-of-the-art research study facility situated in the heart of Chongqing,” it said, then going on to explain the following:

Realising his new reality and “seeking to comprehend his function in this strange brand-new world”, he then leaves and meets Zhu Bajie and Sha Wujing – “each fighting with their own existential crises”.

The trio then starts a mission, navigating the streets of Chongqing to safeguard the sacred “Eternal Scroll” from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “tough to make a conclusive statement” about which bot was best, adding that each displayed its own strengths in various areas, “such as language focus, training data and hardware optimization”.

Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather evolving in cost-efficient development methods – and providing localised and enhanced results.

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

DeepSeek’s sci-fi movie plot demonstrated its creative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual actions to questions about Chinese existing events, which offers it an included benefit.

Experts likewise weighed in on their ideas after using 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 company Strategy Risks.

“When provided an option, Chinese users desire the non-censored version – similar to anybody 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 percent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They’re utilizing it for other efficient means,” Chen said.