Ministry of Science and ICT Discloses IndeFAMO Second-Phase Category Scores... LG and SKT Top Two Categories Each

Disclosure of Detailed Indicators and Scores in Response to Transparency Concerns
Overall Company Rankings and Total Scores Remain Confidential

The government has partially disclosed detailed rankings and scores for each category from the second phase evaluation of the Independent Artificial Intelligence (AI) Foundation Model (IndeFAMO) Project. This comes amid controversy over transparency surrounding the results of the second evaluation.

On August 20, the Ministry of Science and ICT revealed the top-ranked company and the detailed score for each entry in the second phase assessment of the IndeFAMO project. However, the overall ranking and total scores for each company were not released this time as well.

Ryu Jemyung, Vice Minister of the Ministry of Science and ICT, is announcing the 'Evaluation Results of the First Phase of the Independent AI Foundation Model Project' at the Government Complex Seoul in Jongno-gu, Seoul, on January 15, 2026. Photo by Yongjun Cho

Previously, on August 18, when announcing the second phase evaluation results, the Ministry of Science and ICT stated that it would not disclose detailed scores and rankings by category. This was due to concerns about the potential stigma effect on companies that did not pass, in addition to the minimal differences in scores between categories. However, following subsequent controversy over transparency, the ministry released information equivalent to what was provided after the first phase, including: ▲ the highest-scoring team in each category ▲ the detailed scores of those teams ▲ and the average scores of the four elite teams.

This second phase evaluation was scored out of a total of 100 points: 40 points for benchmark evaluation, 35 points for expert evaluation, and 25 points for user evaluation.

The 40-point benchmark evaluation consisted of the Artificial Analysis Intelligence Index (AAII, 25 points) and Korea Intelligent Information Society Agency (NIA) benchmark (15 points).

According to the additional data disclosed by the Ministry of Science and ICT, Motif Technologies received the highest converted score in the AAII benchmark evaluation with 11.9 points. Previously, Motif Technologies earned the highest raw score among the four elite teams, scoring 47 points in AAII. The average score among the four teams was reported as 9.48 points.

In another benchmark evaluation indicator, the NIA benchmark assessment, SK Telecom's elite team received the top score with 13.4 points. The average score of the four teams in the NIA benchmark was 13.05 points.

The expert evaluation, worth up to 35 points, was divided into ▲Development Strategy and Technology (10 points), ▲Development Performance and Plan (10 points), and ▲Impact and Contribution Plan (15 points). In this assessment, the LG AI Research elite team ranked first with 29.5 points. The average expert evaluation score of the four teams was 28.75 points.

The Ministry of Science and ICT explained, "To ensure fair competition between the newly participating Motif Technologies and the existing elite teams, we evaluated the impact of Motif Technologies' elite team on Korea's AI ecosystem by comprehensively considering both the field deployment achievements and plans of their existing AI models, not just those based on the new independent AI model," adding, "This was a matter of consensus among the elite teams."

The user evaluation comprised 15 points from expert AI users and 10 points from the general public. The expert AI user evaluation included 49 AI startup representatives, while the general public evaluation involved 185 randomly selected individuals who participated through an open call.

In the expert AI user evaluation, SK Telecom received the highest score with 11.6 points, and the average score among the four teams was 10.53 points. In the general public evaluation, the LG AI Research team received the highest score with 7.6 points, and the average score among the four teams was 7.03 points.

An official from the Ministry of Science and ICT stated, "In disclosing the evaluation results, we aimed to minimize any unforeseen harm to individual companies while also balancing the values of fairness and transparency. That is why we released the results of the second phase evaluation." The official added, "We will continue to expand policy support to ensure that not only the elite teams in the IndeFAMO project but also various companies continue to develop their AI models and technologies beyond the achievements of this project."

This content was produced with the assistance of AI translation services.