What GAIA scores mean — how far have AI agents advanced?
When the GAIA benchmark was first released, even GPT-4, which was the leading model at the time, scored only around 30%. Given that GAIA requires complex reasoning, tool use and multi-step problem-solving beyond simple question answering, this meant that AI was still at an early stage in its ability to “think and act”.
However, leading agents have now reached 92.36%.
This change is more than a simple improvement in performance. It indicates that AI has now entered the ‘Agentic AI’ phase, moving beyond answering questions to interpreting situations, selecting the necessary tools, and planning and executing multiple steps independently.
In just a few years, AI has evolved from a “knowledge generation tool” into an “executing agent that performs tasks”.
📌 And CLEVI is among the top 2.5%
In this global competitive environment, CLEVI’s domestically developed agent being listed among the top 2.5% on the GAIA leaderboard demonstrates technological self-reliance and proves that an AI agent created in Korea can meet global standards. This means more than just a number. It signifies technological capability objectively validated through competition with thousands of models on a publicly available global benchmark, rather than in a specific demo environment.
More importantly, this achievement was not the chance result of a single model. Agents with different designs have repeatedly delivered top-tier performance on the same Agent Stack.
In other words, CLEVI’s technology is not a “one-off good result”, but reproducible, structural competitiveness and platform-level capability that can be extended to diverse industries and scenarios.
So, what does this indicator mean?
From the user’s perspective, the biggest barrier to adopting AI is the question: "Can it really be trusted and entrusted with tasks?"
Performance repeatedly proven on the stage of a third-party global public leaderboard—not through flashy demos or company presentations—is the most objective answer to that question. Specifically, it is significant in three respects.
First, reducing adoption risk
Connecting unverified AI to internal business processes represents a considerable burden for businesses.
Performance on credible benchmarks such as GAIA can be used directly as a basis for trust during the technical evaluation stage.
Second, making complex workflow automation a reality
A ranking in the top 2.5% signifies a level of intelligence that goes beyond simple repetitive tasks, understanding context and independently making decisions across multiple steps to complete them.
Areas of work previously considered “too difficult to entrust to AI” can become practical targets for automation.
Third, securing data protection and performance simultaneously
The proprietary Agent Stack architecture means that data flows do not leave the organisation.
This makes it possible to move beyond the previous dilemma of having to compromise security in order to use high-performance AI.
This architecture is a decisive differentiator, particularly in industries with highly sensitive data, such as finance, healthcare and legal services.
The reproducibility of this architecture is already beginning to be proven.
And the performance of each agent built on that architecture will soon lead to tangible change in the field.
“Ultimately, technological excellence is completed by ‘confidence’ in the field.”
CLEVI does not simply provide high-performance AI. Our essence lies in building an ‘execution-ready infrastructure’ that breaks down the security barriers businesses face and actually completes complex day-to-day work.
Now, move beyond considering adoption and start a safe and powerful AI work environment with CLEVI.
As a dependable partner you can trust with your work, we will work with you to create tangible innovation in your business.