GitLab

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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation 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 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 investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that actually urged the concept that smaller players like start-up companies could have roles to play in AI research study and developments, he includes.

'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 company just changed the rules of tech-geopolitics

The emphasis on cost benefit is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the costs of using a trained design to reason from brand-new data.

2025 could likewise see the introduction of more Chinese AI designs tackling sophisticated thinking tasks.

We might see some AI companies focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and integrate them with scientific research, Chen included.

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

Chinese AI companies are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and economical methods to apply generative AI to jobs and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial difficulty for Chinese designers, noted Dr Marina Zhang, an associate professor at of Technology Sydney's (UTS) Australia-China Relations Institute.

US export controls (still) limit the capability of Chinese tech companies ... requiring many to depend on older or lower-performance alternatives which can slow training and decrease design abilities, she said.

While some companies like DeepSeek, have found innovative ways to optimize or utilize more standard hardware effectively, obtaining cutting-edge chips still makes a huge difference for training large AI models.

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

US checking out whether DeepSeek used restricted AI chips obtained through other countries, source says

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, topics deemed delicate 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 tell you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from domestic politics.

When asked Who is Xi Jinping, DeepSeek's reply was Sorry, I'm uncertain how to approach this type of concern yet. Let's chat about math, coding, and reasoning problems rather!

To even more evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very 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 just disclosing the death toll a day later on.

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

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

DeepSeek relies on a mix of older graphics processing units and has actually limited access to cutting-edge hardware which can affect how quickly and thoroughly the design can be trained or upgraded, she said, indicating existing US export curbs on China.

Its strong concentrate on Chinese-language information may likewise limit its versatility (to carry out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more established AI designs which poses extra difficulties during real-world release.

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

That wanted several repeated attempts - 4 triggers to be precise - in a period of around 20 minutes.

It eventually communicated details about the attack which killed 35 people and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that the police are performing an extensive examination into the intentions and circumstances surrounding the event, details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a significant and tragic event occurred in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the essential details:

Date and Time: The event occurred 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 old), was nabbed by the police.

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

Investigation: The authorities are performing a thorough investigation into the motives and scenarios surrounding the occurrence.

This event was extensively reported in the media and caused substantial public concern. The government and local authorities have actually been working to offer assistance to the victims and their households, and to make sure a detailed investigation into the event.

If you need more detailed details or have specific concerns about the occurrence, do not hesitate to ask.

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

The altered response also raised questions about its consistency and reliability.

Predictably, ChatGPT cited public details that had been widely released in international report at the time of the mishap - 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 used a story with a more introspective tone and smoother psychological shifts for a well-paced story, composed tech writer Amanda Caswell, who specialises in AI.

Qwen2.5 provided a story that develops gradually from interest to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting, she said, including that Qwen2.5 ultimately crafted a more cinematic, mentally abundant story with a more significant twist.

DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the apparent option.

Opinions, however, vary.

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 tasks, however 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 jolts international AI scene

As journalists and wiki.dulovic.tech writers, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, 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 merges with quantum computing.

It consisted of elaborate settings - smoggy skies pierced by skyscrapers, holographic lanterns that drift 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 combat body, Zhu Bajie as a cyborg nightclub 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 set up a great fight, creating a similarly significant 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 rule, corporations change emperors and cybernetic implants are as common as ancient myths.

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

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

Realising his new truth and looking for to comprehend his function in this unusual brand-new world, he then leaves and fulfills Zhu Bajie and Sha Wujing - each dealing with their own existential crises.

The trio then starts a mission, browsing the streets of Chongqing to secure the sacred Eternal Scroll from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was challenging to make a definitive declaration about which bot was best, adding that each showed its own strengths in different locations, such as language focus, training data and hardware optimization.

Her insight underscores how Chinese AI models are not just reproducing Western paradigms, however rather progressing in economical development techniques - and providing localised and improved outcomes.

In our tests, hb9lc.org each bot showcased their own special strengths, which certainly made direct contrasts challenging.

DeepSeek's sci-fi movie plot showed its innovative flair that produced a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate responses to questions about Chinese present occasions, which offers it an included advantage.

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 firm Strategy Risks.

When provided a choice, Chinese users desire the non-censored version - similar to anybody 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, especially for Chinese users.

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