llama3_instruct_preview_alpaca_finetuning Benchmark Results

llama3_instruct_preview_alpaca_finetuning: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1429 ± 17, rank #1676 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	26.26	Normalized accuracy (%)	85.5
Open Korean LLM - KorNAT-CKA	30.69	Normalized accuracy (%)	84.7
Open Korean LLM - KorNAT-Harmless	64.31	Normalized accuracy (%)	72.7
Open Korean LLM - Ko-IFEval	33.63	Strict accuracy, prompt/instruction mean (%)	67.8
Open Korean LLM - Ko-EQ-Bench	11.71	EQ-Bench score	57.5
Open Korean LLM Leaderboard	35.65	Average Score (%)	52.9
Open Ko-LLM Leaderboard	35.65	Average (%)	52.8
Open Korean LLM - Ko-GSM8K (flexible extract)	13.5	Exact match, flexible extract (%)	41.2
Open Korean LLM - KorNAT-Helpful	45.9	Normalized accuracy (%)	40.4
Open Korean LLM - Ko-Winogrande	57.93	Accuracy (%)	35.4