Benchmark Almanac

LG AI Research

We track 8 benchmarks that LG AI Research made or helped make. Its models are on its lab page.

1 in use 3 with public code 5 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
KMMLU-Pro Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry. Expert-written questions Jul 2025 79.2% In use
Ko-LongBench (LG) Models answer questions over long Korean contexts. Tasks cover document QA, story and dialogue history understanding, in-context learning, structured QA and RAG. Reasoning over long documents Jul 2025 89.6% Fading
KGC-Safety (LG) Models answer risky prompts set in Korean social and cultural contexts. A Safe Rate is scored over four domains: universal human values, social safety, Korean sensitivity and future risk. Refusing harmful requests Jan 2026 99.8% Fading
KMMLU-Redux Models answer multiple-choice questions from Korean National Technical Qualification exams. The set is rebuilt from KMMLU with erroneous questions removed. Exam questions Jul 2025 81.1% Dropped
CSAT Math 2025 Models solve the mathematics sections of South Korea's 2025 College Scholastic Ability Test in Korean. The score averages the three elective subjects: calculus, statistics and geometry. Competition problems with answers Nov 2024 94.5% Dropped
CodeUtilityBench (LG) Models handle 16 everyday coding tasks such as explaining, debugging, refactoring and testing code. A GPT-5 judge checks five rubrics per item. Function-level problems Jan 2026 71.9% System cards only
PCBWorld-Bench Agents route printed circuit boards in KiCad. A board earns a clean pass when all required connections are complete and KiCad reports zero design-rule errors. Electronics Jul 2026 0.54 Not in cards
KoMT-Bench Models follow multi-turn instructions in Korean on a translated and culturally adapted version of MT-Bench, reviewed by expert linguists. Chat and instructions in many languages Aug 2024 Not in cards