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 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 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 China has its sights on ending up being 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 researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and revealed pledges of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller players like start-up firms could have functions to play in AI research study and developments, he includes.

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

Commentary: pipewiki.org DeepSeek - how a Chinese AI company just altered the rules of tech-geopolitics

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

2025 might likewise see the introduction of more Chinese AI designs tackling innovative thinking jobs.

"We could see some AI firms concentrating on getting closer to artificial general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with scientific research study," Chen included.

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

Chinese AI companies are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to jobs and establish more innovative products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential hurdle for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech companies ... requiring numerous to depend on older or lower-performance options which can slow training and lower model capabilities," she said.

"While some business like DeepSeek, have found creative methods to enhance or use more fundamental hardware effectively, obtaining innovative chips still makes a huge difference for training huge AI models."

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

US looking into whether DeepSeek used restricted 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, subjects deemed sensitive by the state are censored on the web so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and reasoning issues instead!"

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

The cars and truck attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had actually taken location, highlighting instead a military air program and other events that had actually taken place in the city like songs' day shopping sales as well as 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 systems and has actually limited access to advanced hardware which can impact how quickly and thoroughly the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language data may likewise restrict its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more established AI designs which poses extra challenges throughout real-world release."

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

That wanted multiple repeated attempts - four prompts to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and 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 wrote that "the police are performing a thorough examination into the intentions and situations surrounding the event", details which is now outdated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

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

Date and Time: photorum.eclat-mauve.fr The occurrence took place on November 11, 2024, at roughly 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.

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

Investigation: The police are conducting a comprehensive investigation into the intentions and situations surrounding the occurrence.

This occasion was extensively reported in the media and caused significant public issue. The federal government and regional authorities have actually been working to offer support to the victims and their families, and to ensure a detailed investigation into the event.

If you need more detailed details or have particular questions about the occurrence, setiathome.berkeley.edu do not hesitate to ask.

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

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

Predictably, ChatGPT mentioned public details that had actually been commonly released in worldwide report 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 deliver structured and even "mentally abundant" writing.

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

"Qwen2.5 delivered a story that constructs gradually from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more substantial twist".

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

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as highly as others in innovative writing," he informed 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 shocks global AI scene

As journalists 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, including main characters from the classic Chinese folklore epic, Journey to the West.

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

It included fancy 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 remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub 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 battle, developing a similarly remarkable cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

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

"The film begins with the awakening of Sun Wukong within a high-tech research study facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "seeking to comprehend his purpose in this strange new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather developing in cost-effective innovation techniques - and delivering localised and enhanced outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by constraints, offers precise and accurate reactions to questions about Chinese present occasions, which offers it an added benefit.

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

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

"When given an option, Chinese users want the non-censored version - simply like anyone else, so I feel 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 utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient means," Chen said.