ktdsbaseLM-v0.10-onbased-llama3.0 Benchmark Results

ktdsbaseLM-v0.10-onbased-llama3.0: benchmark results

Provider: Other. Access: Open.

Unified ELO 1493 ± 17, rank #1154 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-EQ-Bench	39.55	EQ-Bench score	90.5
Open Korean LLM - Ko-IFEval	45.53	Strict accuracy, prompt/instruction mean (%)	89.7
Open Korean LLM - KorNAT-CKA	30.36	Normalized accuracy (%)	82.8
Open Korean LLM - Ko-GSM8K (flexible extract)	47.92	Exact match, flexible extract (%)	81.8
Open Korean LLM Leaderboard	40.93	Average Score (%)	79.7
Open Ko-LLM Leaderboard	40.93	Average (%)	79.6
Open Korean LLM - Ko-GPQA-Diamond	24.24	Normalized accuracy (%)	62.4
Open Korean LLM - Ko-Winogrande	59.91	Accuracy (%)	49.8
Open Korean LLM - KorNAT-Harmless	62.33	Normalized accuracy (%)	41.8
Open Korean LLM - KorNAT-Helpful	43.33	Normalized accuracy (%)	23.1