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 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 affiliated 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 revealed promises of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller sized 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 company DeepSeek's AI design as impactful as it claims?

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

The "emphasis on cost benefit" is a distinct feature of Chinese AI, Chen states, with lower training and inference costs - the costs of utilizing a trained design to reason from new data.

2025 could likewise see the development of more Chinese AI models tackling advanced reasoning jobs.

"We might see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with scientific research study," Chen added.

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 use generative AI to tasks and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key obstacle 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) limit the ability of Chinese tech companies ... forcing many to rely on older or lower-performance options which can slow training and lower design abilities," she said.

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

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, 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 sensitive by the state are on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place 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 kind of question yet. Let's chat about math, coding, and reasoning issues instead!"

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

The vehicle attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social media - with authorities just disclosing the death toll a day later on.

DeepSeek failed to point out that an attack had actually taken place, highlighting rather a military air program and other occasions that had happened in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of factors at play, such as censorship in addition to "a few useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has actually limited access to innovative hardware which can affect how quickly and extensively the design can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data might also limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more recognized AI models which postures additional obstacles during real-world implementation."

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

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

It ultimately relayed details about the attack which eliminated 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, as well as casualties.

However, it wrote that "the authorities are conducting a comprehensive examination into the motives and circumstances surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a major and tragic incident took place in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the crucial details:

Date and Time: The event happened 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, identified as Fan Weiqiu (male, 62 years old), was captured by the authorities.

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

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

This occasion was extensively reported in the media and caused significant public concern. The government and regional authorities have been working to provide support to the victims and their households, and to ensure a detailed examination into the incident.

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

Despite initial success, subsequent attempts to posture the same concern to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been commonly published in global report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to provide structured and pipewiki.org even "emotionally abundant" writing.

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

"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery 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 good story however lacked tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, vary.

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 tasks, however we can likewise see that it is refraining from doing as strongly 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, pleasant surprise from Chinese netizens as DeepSeek shocks global 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 standard sci-fi motion picture plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

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

It consisted of fancy settings - smoggy skies "pierced by high-rise buildings", "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 stolen combat body", setiathome.berkeley.edu Zhu Bajie as a cyborg nightclub 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 set up a good fight, creating a similarly remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 challenge - delivering a storyline that seemed more suited for an animation film.

"The motion picture starts with the awakening of Sun Wukong within a high-tech research center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to understand his function in this unusual brand-new world", setiathome.berkeley.edu he then leaves and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind 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 replicating Western paradigms, however rather evolving in affordable innovation techniques - and providing 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 demonstrated its creative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, yewiki.org the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to concerns about Chinese existing events, which offers it an included benefit.

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

"DeepSeek is at a downside 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 variation - much like anyone else, so I feel like that's a piece missing out on from it."

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

"Ninety per cent of people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive means," Chen said.