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, wiki.snooze-hotelsoftware.de AFP/Sebastien Bozon)

This audio is produced 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 goal and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically essential" and its venture into the field has actually 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 investments in Chinese AI accelerated after ChatGPT removed 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 companies could have roles to play in AI research and developments, he adds.

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

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

The "emphasis on cost advantage" is a distinctive function of Chinese AI, Chen says, with lower training and reasoning costs - the costs of utilizing a trained design to draw conclusions from brand-new data.

2025 might likewise see the development of more Chinese AI designs taking on advanced thinking jobs.

"We might see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research," Chen included.

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

Chinese AI business are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own innovative and affordable ways to apply generative AI to tasks and wiki.snooze-hotelsoftware.de develop advanced products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key obstacle for Chinese developers, hb9lc.org noted 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 business ... requiring lots of to count on older or lower-performance options which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have actually discovered creative ways to optimize or use more basic hardware effectively, obtaining innovative chips still makes a big difference for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it anticipates business to comply with its laws

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, source states

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 considered sensitive 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 inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to avoid domestic politics.

When asked "Who is Xi Jinping", demo.qkseo.in DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and reasoning problems instead!"

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

The automobile attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had actually taken location, highlighting instead a military air show and other events that had happened 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 in addition to "a couple of practical constraints".

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

"Its strong concentrate on Chinese-language data may also limit its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been tested as broadly or on the very same scale as more recognized AI models which presents 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 was after numerous repeated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It ultimately relayed details about the attack which killed 35 people and left dozens of others hurt, also 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 performing an extensive investigation into the motives and scenarios surrounding the occurrence", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible event happened in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the key details:

Date and Time: The occurrence happened 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, recognized as Fan Weiqiu (male, 62 years of ages), was apprehended by the police.

Response: The authorities responded rapidly to the scene, and emergency situation services worked to transport the hurt to hospitals for treatment.

Investigation: The police are performing an extensive investigation into the intentions and scenarios surrounding the incident.

This event was extensively reported in the media and caused considerable public issue. The government and regional authorities have actually been working to offer assistance to the victims and their families, and to guarantee a detailed investigation into the incident.

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

Despite initial success, subsequent attempts to pose the exact same concern to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT mentioned public details that had been extensively published in international news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered a story with a more reflective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more significant twist".

"DeepSeek wrote a good story however did not have tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out 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 likewise see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?

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

As reporters 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 film plot set in the futuristic megacity of Chongqing, featuring 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 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken battle body", Zhu Bajie as a cyborg club owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a great fight, developing a similarly dramatic cyberpunk storyline which similarly 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 myths."

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

"The motion picture begins 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 new reality and "looking for to comprehend his purpose in this unusual new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not merely reproducing Western paradigms, however rather progressing in affordable development techniques - and delivering localised and improved results.

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

DeepSeek's sci-fi movie plot demonstrated its imaginative flair that produced 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 precise and factual reactions to questions about Chinese present occasions, which gives it an added advantage.

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

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

"When provided a choice, Chinese users want the non-censored variation - just like anybody 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, particularly for Chinese users.

"Ninety per cent of individuals using the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other productive ways," Chen said.