LG AI Research, SK Telecom, and Upstage have advanced to the next stage in the second-phase evaluation for the development of South Korea's flagship Independent AI Foundation Model project.
The Ministry of Science and ICT announced that, following a comprehensive evaluation combining benchmarks, expert reviews, and user assessments, Motif Technologies finished at the bottom among the four elite teams and was eliminated.
In the benchmark evaluation, which was worth 40 points, the overall average for the four teams was 22.5 points, with a 4.0-point gap between the first-place and fourth-place teams.
The expert evaluation, carrying a weight of 35 points, recorded an overall average of 28.8 points, with a 2.4-point gap between the first-place and fourth-place teams.
The user evaluation, worth 25 points, had an overall average of 17.6 points, with a 5.0-point gap between the first-place and fourth-place teams.
※
Copying, redistribution, and unauthorized use in AI training are strictly prohibited.