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

China views AI as being "strategically important" and its venture into the field has been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's increase that truly "urged" the concept that smaller sized gamers like start-up companies could have roles to play in AI research study and developments, he adds.

'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 simply changed the rules of tech-geopolitics

The "focus on cost benefit" is a distinctive function of Chinese AI, Chen says, with lower training and inference costs - the costs of utilizing a trained model to reason from new data.

2025 might also see the development of more Chinese AI models dealing with sophisticated thinking jobs.

"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others focus 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 companies are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to jobs and develop advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial 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 ability of Chinese tech companies ... forcing numerous to rely on older or lower-performance options which can slow training and reduce design capabilities," she said.

"While some companies like DeepSeek, have discovered innovative methods to enhance or utilize more standard hardware effectively, obtaining advanced chips still makes a big difference for training extremely big AI models."

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

US looking into whether DeepSeek utilized 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, topics considered sensitive by the state are censored on the web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to guide clear of 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 math, coding, and logic issues instead!"

To further test for precision and self-censorship, we asked DeepSeek-R1, wiki.myamens.com Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"

The automobile attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social media - with authorities only divulging the death toll a day later on.

DeepSeek failed to discuss that an attack had occurred, highlighting rather a military air show and other occasions that had taken place in the city like singles' day shopping sales in addition to 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 practical constraints".

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

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

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

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

It ultimately relayed details about the attack which eliminated 35 people and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the cops are performing a thorough examination into the intentions and circumstances surrounding the incident", details which is now outdated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a major and awful event happened in Zhuhai, China. According to several news sources, a male named 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 considerable number of casualties. Here are the crucial details:

Date and Time: The occurrence occurred 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.

Response: The police responded rapidly to the scene, and emergency situation services worked to carry the hurt to healthcare facilities for treatment.

Investigation: The authorities are carrying out a comprehensive examination into the motives and situations surrounding the event.

This occasion was extensively reported in the media and caused substantial public concern. The federal government and regional authorities have been working to provide assistance to the victims and their households, and to guarantee a detailed investigation into the occurrence.

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

Despite preliminary success, links.gtanet.com.br subsequent attempts to position the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had actually been extensively published in global news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided 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 builds gradually from interest to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more considerable twist".

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

Opinions, though, vary.

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 tasks, however we can also see that it is refraining from doing as strongly 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, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide 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 movie plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, Journey to the West.

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

It included fancy settings - smoggy skies "pierced by skyscrapers", "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 taken 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 battle, coming up with an equally dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

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

"The movie starts with the awakening of Sun Wukong within a modern research study 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 purpose in this unusual new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each having problem 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 under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, however rather evolving in cost-effective innovation methods - and delivering 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 demonstrated its imaginative flair that produced a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, forum.altaycoins.com unburdened by Chinese censorship constraints, supplies accurate and accurate reactions to questions about Chinese existing events, which offers it an included advantage.

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

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

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

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for 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 methods," Chen said.