[Edaily Reporter Kim Hyun-ah ] Among the four models participating in the “Domestic AI National Team” selection process—the Independent AI Foundation Model Project (Dokpamo)—Motif’s “Motif 3” received the highest score in the latest evaluation by Artificial Analysis, a global artificial intelligence (AI) evaluation agency.

According to Artificial Analysis on the 13th, Motif 3 scored 47 points in the latest “Artificial Analysis Intelligence Index v4.1.1.” Following Motif 3 were Upstage’s “Solar Open2 250B” with 37 points, SKTelecom(017670)’s “A.X-K2” with 35 points, and the AI Research Institute at LG Corp.(003550) ’s “K-EXAONE 2.0 0803” with 31 points.

Artificial Analysis is a global AI analytics organization that comprehensively evaluates various capabilities of AI models, including mathematics, science, coding, and reasoning. The latest Intelligence Index calculates scores by synthesizing results from nine evaluations, including GDPval-AA v2, τ³-Banking, Terminal-Bench 2.1, SciCode, Humanity’s Last Exam, and GPQA Diamond.

Meanwhile, with the announcement of the results of the third evaluation for the “Independent AI Foundation Model” (IAFM) project imminent, the AAII score—a global benchmark—is expected to have a significant impact on the final review. In this third evaluation, one of the four companies—LG Corp., Upstage, SKTelecom, and Motif Technologies—will be eliminated.

It is reported that the AAII score accounts for 25 points out of the 40-point benchmark for the second round of the Dokpamo evaluation. The remaining 15 points are based on the National Information Society Agency (NIA)’s internal benchmark. Since the AAII score accounts for 25% of the total 100 points, it is expected to have a significant impact on the final rankings.

AAII is a global benchmark that evaluates practical AI application capabilities, such as reasoning, knowledge, and coding. An official from the Ministry of Science and ICT stated, “Typically, companies commission the AAII evaluation themselves, but this time, the government directly commissioned Artificial Analysis, resulting in the scores being made public.”