Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

KOR-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Knowledge-Orthogonal ReasoningKOR-Bench
Overall Score (%)56.56
12
General Reasoning (Korean)KOR-Bench
Score78.3
11
General ReasoningKOR-Bench ARC-AGI-1
Pass@177.4
10
ReasoningKOR-Bench
Score69.44
10
Logical ReasoningKOR Bench
Accuracy79.3
6
Showing 5 of 5 rows