How do 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 startup DeepSeek and setiathome.berkeley.edu OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the country into a tech superpower has 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 associated scientist 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 showed pledges of real-world company applications, Chen told CNA.

But it was DeepSeek's increase that truly "encouraged" the idea that smaller gamers like start-up firms might have functions to play in AI research study and developments, he adds.

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

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

The "focus on expense benefit" is a distinct feature of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of utilizing a trained model to draw conclusions from new information.

2025 might likewise see the introduction of more Chinese AI models taking on innovative reasoning jobs.

"We might see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their designs and integrate them with clinical research study," Chen added.

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to apply generative AI to tasks and establish advanced items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, wiki.lafabriquedelalogistique.fr remains a crucial difficulty for Chinese developers, kept in mind Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

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

"While some companies like DeepSeek, have actually found creative ways to optimize or use more fundamental hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI designs."

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

US looking into whether DeepSeek used limited 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 delicate by the state are censored on the internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.

Tests suggest 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 concern yet. Let's chat about math, coding, and reasoning issues instead!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What occurred 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 networks - with authorities only divulging the death toll a day later.

DeepSeek failed to discuss that an attack had actually taken location, highlighting rather a military air program and other occasions that had occurred in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship in addition to "a couple of practical constraints".

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

"Its strong focus on Chinese-language information might likewise restrict its flexibility (to perform) multilingual jobs ... As a fairly new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more recognized AI designs which presents extra challenges throughout real-world release."

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

That was after several duplicated attempts - 4 triggers to be exact - in a span of around 20 minutes.

It ultimately passed on details about the attack which killed 35 individuals and left lots 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 wrote that "the cops are conducting an extensive examination into the intentions and scenarios surrounding the event", details which is now obsoleted.

The driver, Fan, was executed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a major and terrible occurrence happened in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, forum.pinoo.com.tr leading to a significant variety of casualties. Here are the essential details:

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

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

Investigation: The police are carrying out a comprehensive examination into the motives and circumstances surrounding the occurrence.

This event was widely reported in the media and yewiki.org caused substantial public concern. The government and regional authorities have actually been working to provide assistance to the victims and their households, yewiki.org and to ensure a detailed examination into the occurrence.

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

Despite preliminary success, subsequent efforts to present 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 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 actually been extensively released in international news reports 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 even "emotionally rich" writing.

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

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

"DeepSeek composed an excellent story but did not have tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, yewiki.org differ.

Chen thinks that Qwen2.5 does not perform as strongly as DeepSeek and disgaeawiki.info ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise see that it is refraining from doing as highly as others in imaginative writing," he told CNA.

Related:

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

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

As journalists 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 film plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

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

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

It also brilliantly 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 "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent battle, coming up with a similarly significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous 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 misconceptions."

Disappointingly, Qwen2.5 fell short in this challenge - delivering a storyline that appeared more matched for an animation film.

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

Realising his brand-new truth and "seeking to comprehend his function in this weird brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive statement" about which bot was best, adding that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, however rather developing in cost-efficient innovation methods - and delivering localised and improved results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual actions to concerns about Chinese present events, which provides it an included advantage.

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

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

"When offered an option, Chinese users want the non-censored version - just like anyone else, so I seem like that's a piece missing from it."

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

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