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 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 “strategically essential” and its venture 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 sped up after ChatGPT took off in 2022 and showed pledges of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s rise that really “encouraged” the idea that smaller gamers like start-up companies 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 model as impactful as it claims?

Commentary: DeepSeek – how a Chinese AI company simply changed the guidelines of tech-geopolitics

The “emphasis on cost advantage” is a distinctive feature of Chinese AI, pipewiki.org Chen says, with and reasoning costs – the expenses of using a trained model to reason from new information.

2025 might also see the introduction of more Chinese AI designs tackling advanced reasoning jobs.

“We could see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with scientific research study,” Chen added.

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

Chinese AI business are moving rapidly, experts say, building on DeepSeek’s momentum to come up with their own ingenious and cost-effective ways to use generative AI to tasks and develop more sophisticated products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia’s innovative AI chips, remains a key difficulty for Chinese developers, 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 alternatives which can slow training and lower model capabilities,” she said.

“While some companies like DeepSeek, have actually discovered creative ways to optimize or utilize more standard hardware efficiently, obtaining advanced chips still makes a big distinction for training large AI models.”

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

US looking into whether DeepSeek used limited AI chips obtained through other countries, source states

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, topics considered delicate by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid 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 mathematics, coding, and reasoning issues instead!”

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

The cars and truck attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks – with authorities only divulging the death toll a day later on.

DeepSeek failed to point out that an attack had happened, highlighting rather a military air show and other occasions that had occurred in the city like songs’ day shopping sales in addition to sports and cultural activities.

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

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

“Its strong concentrate on Chinese-language data might also restrict its versatility (to perform) multilingual tasks … As a fairly new item, DeepSeek also hasn’t yet been checked as broadly or on the very same scale as more established AI models which poses extra difficulties 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 duplicated attempts – 4 prompts to be exact – in a span of around 20 minutes.

It eventually relayed details about the attack which killed 35 people and wiki.dulovic.tech left dozens of others injured, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that “the authorities are performing an extensive investigation into the intentions and circumstances surrounding the incident”, details which is now dated.

The driver, Fan, was performed last month.

This is Qwen2.5’s response completely:

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

Date and Time: The event 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, identified as Fan Weiqiu (male, 62 years of ages), was captured by the police.

Response: The cops responded rapidly to the scene, and emergency situation services worked to transport the injured to medical facilities for treatment.

Investigation: The cops are conducting a comprehensive investigation into the motives and scenarios surrounding the incident.

This event was widely reported in the media and triggered significant public issue. The government and regional authorities have actually been working to offer assistance to the victims and their families, and to ensure a detailed examination into the occurrence.

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

Despite initial success, subsequent efforts to posture the very same question to Qwen2.5 led to 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 transformed reaction also raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been commonly 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 “emotionally abundant” writing.

“DeepSeek-R1 provided 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 provided a story that develops gradually from curiosity to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting,” she said, including that Qwen2.5 ultimately “crafted a more cinematic, emotionally abundant story with a more significant twist”.

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

Opinions, however, vary.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to imaginative 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 imaginative writing,” he told CNA.

Related:

China’s new face of AI: Who is DeepSeek creator Liang Wenfeng?

‘Made in China’: Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide AI scene

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

True to form, DeepSeek created an engaging story embeded in the year 2145 titled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

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

It also remarkably reimagined traditional heroes Sun Wukong as “a sarcastic, self-aware AI housed in a taken fight 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 end up being waterlogged and fragmented”.

ChatGPT put up an excellent fight, developing an equally remarkable 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 replace emperors and cybernetic implants are as typical as ancient myths.”

Disappointingly, Qwen2.5 fell short in this difficulty – providing a storyline that appeared more suited for an animation movie.

“The motion picture starts with the awakening of Sun Wukong within a state-of-the-art research study facility located 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 weird new world”, he then gets away and meets Zhu Bajie and Sha Wujing – “each dealing with their own existential crises”.

The trio then embarks on a mission, navigating the streets of Chongqing to protect the spiritual “Eternal Scroll” from falling into the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely reproducing Western paradigms, however rather progressing in cost-effective innovation techniques – and providing localised and improved outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and wiki.vst.hs-furtwangen.de accurate actions to concerns about Chinese present events, which offers it an included benefit.

Experts likewise weighed in on their ideas after utilizing DeepSeek and other Chinese AI apps.

“DeepSeek is at a disadvantage when it pertains to censorship constraints,” kept in mind Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

“When given an option, Chinese users want the non-censored version – just like anybody else, so I seem like that’s a piece missing from it.”

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

“Ninety per cent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive subjects. They’re utilizing it for other efficient means,” Chen said.