Benchmark profile
Cultural and Linguistic Intelligence in Korean (CLIcK)
Evaluates Korean culture and linguistics.
Data verifiedHow BenchLM shows CLIcK right now
BenchLM is tracking CLIcK in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.
These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.
Tracked score on CLIcK — July 23, 2026
BenchLM mirrors the published tracked score view for CLIcK. K-Exaone leads the public snapshot at 83.9%. BenchLM does not use these results to rank models overall.
K-Exaone
LG AI Research
k-exaone
Tracked score table (1 model)
ScoreAbout CLIcK
Tasks
1,995 questions
Format
Cultural/linguistic QA
Difficulty
Korean cultural nuances
BenchLM freshness & provenance
Version
CLIcK
Refresh cadence
Static
Staleness state
Refreshing
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does CLIcK measure?
Evaluates Korean culture and linguistics.
Which model leads the published CLIcK snapshot?
K-Exaone currently leads the published CLIcK snapshot with 83.9% tracked score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on CLIcK?
1 AI models are included in BenchLM's mirrored CLIcK snapshot, based on the public leaderboard captured on July 23, 2026.
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.