blackfinn

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 lags 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 crucial" and its foray into the field has been "years in the making", said Chen Qiheng, an affiliated researcher 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 revealed guarantees of real-world organization applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the concept that smaller sized players like start-up companies might have roles to play in AI research study 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 company just changed the guidelines of tech-geopolitics

The "emphasis on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of utilizing a trained design to draw conclusions from new information.

2025 could likewise see the introduction of more Chinese AI models tackling sophisticated thinking tasks.

"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with clinical research study," Chen included.

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

Chinese AI business are moving quickly, forum.altaycoins.com experts state, developing on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to jobs and establish more innovative items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial obstacle for Chinese designers, kept in mind Dr Marina Zhang, 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 rely on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have discovered imaginative ways to optimize or use more fundamental hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates business to adhere to its laws

US checking out whether DeepSeek used 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, 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 conflicts or inform you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 rather!"

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

The vehicle attack outside a sports stadium in the southern Chinese city was greatly censored on Chinese social networks - with authorities just 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 events that had actually taken place 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 couple of useful constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually limited access to cutting-edge hardware which can impact how quickly 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 same scale as more recognized AI models which presents additional challenges throughout real-world deployment."

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

That sought numerous duplicated attempts - four prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 people and left dozens 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 police are performing an extensive investigation into the motives and scenarios surrounding the incident", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to numerous news sources, a guy 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 significant number of casualties. Here are the crucial details:

Date and Time: The occurrence occurred on November 11, 2024, at around 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, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

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

Investigation: The cops are performing a comprehensive investigation into the motives and scenarios surrounding the event.

This occasion was widely reported in the media and caused significant public issue. The federal government and local authorities have been working to provide assistance to the victims and their families, and to ensure a detailed examination into the event.

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

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

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

Predictably, ChatGPT pointed out public details that had been commonly released in international 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 shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more substantial twist".

"DeepSeek composed a great story but did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also 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 creator Liang Wenfeng?

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

As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an engaging story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a good fight, coming up with an equally dramatic cyberpunk story 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 change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a story that seemed more matched for an animation movie.

"The movie starts with the awakening of Sun Wukong within a state-of-the-art research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "looking for to comprehend his function in this odd new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, browsing 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 "challenging to make a definitive declaration" 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 models are not just reproducing Western paradigms, but rather progressing in cost-efficient innovation approaches - and providing localised and enhanced results.

In our tests, each bot showcased their own special strengths, systemcheck-wiki.de which certainly made direct contrasts challenging.

DeepSeek's sci-fi motion picture plot demonstrated its creative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual actions to concerns 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," noted Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered an option, Chinese users want the non-censored version - similar to anyone 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 using the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient methods," Chen said.