Llama 3 10B IT Kor Extented Chang Benchmark Results

Llama 3 10B IT Kor Extented Chang: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1503 ± 17, rank #1083 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Ko-LLM Leaderboard	41.99	Average (%)	84.4
Open Korean LLM Leaderboard	41.99	Average Score (%)	84.4
Open Korean LLM - Ko-GPQA-Diamond	25.76	Normalized accuracy (%)	81.3
Open Korean LLM - KorNAT-CKA	29.69	Normalized accuracy (%)	81
Open Korean LLM - Ko-GSM8K (flexible extract)	44.66	Exact match, flexible extract (%)	79.7
Open Korean LLM - Ko-EQ-Bench	27.43	EQ-Bench score	74.5
Open Korean LLM - Ko-IFEval	35.81	Strict accuracy, prompt/instruction mean (%)	74.1
Open Korean LLM - Ko-Winogrande	61.72	Accuracy (%)	63.7
Open Korean LLM - KorNAT-Helpful	45.27	Normalized accuracy (%)	35.6
Open Korean LLM - KorNAT-Harmless	61.46	Normalized accuracy (%)	29.2