Gaiel Korean LLM Benchmark (LogicKor Results)

LOGICKOR_REPORT.md

Gaiel Series Korean Intelligence Benchmark (LogicKor)

Evaluated with GPT-4o Judge across 6 core Korean language & reasoning domains.

Overall Score Leaderboard

Model	Single Turn	Multi Turn	Overall Score (10점 만점)
Gaiel-1.5B-Korean-Tuned-MLX	2.15	1.60	1.87
Gaiel-7B-Korean-Tuned-MLX	4.75	3.60	4.18
Gaiel-32B-Korean-Tuned-MLX	8.67	7.41	8.04

Category Breakdown

encredible/Gaiel-1.5B-Korean-Tuned-MLX

Category	Single Turn	Multi Turn
추론(Reasoning)	1.76	1.10
수학(Math)	2.38	1.81
글쓰기(Writing)	2.14	1.90
코딩(Coding)	2.40	1.85
이해(Understanding)	2.86	1.95
문법(Grammar)	1.30	0.95
Overall	2.15	1.60 (Avg: 1.87)

encredible/Gaiel-7B-Korean-Tuned-MLX

Category	Single Turn	Multi Turn
추론(Reasoning)	5.95	3.62
수학(Math)	5.81	4.43
글쓰기(Writing)	3.14	2.57
코딩(Coding)	4.33	3.38
이해(Understanding)	6.05	4.86
문법(Grammar)	3.24	2.76
Overall	4.75	3.60 (Avg: 4.18)

encredible/Gaiel-32B-Korean-Tuned-MLX

Category	Single Turn	Multi Turn
수학(Math)	9.57	9.05
추론(Reasoning)	8.33	5.57
글쓰기(Writing)	8.95	7.14
코딩(Coding)	9.43	8.62
이해(Understanding)	8.57	8.24
문법(Grammar)	7.14	5.86
Overall	8.67	7.41 (Avg: 8.04)