ktdsbaseLM-v0.14-onbased-llama3.1 Benchmark Results

ktdsbaseLM-v0.14-onbased-llama3.1: benchmark results

Provider: Other. Access: Open.

Unified ELO 1309 ± 18, rank #2426 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - KorNAT-Harmless	65.03	Normalized accuracy (%)	78.7
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-GPQA-Diamond	21.21	Normalized accuracy (%)	24
Open Korean LLM - Ko-IFEval	20.37	Strict accuracy, prompt/instruction mean (%)	18.7
Open Korean LLM Leaderboard	29.03	Average Score (%)	9.3
Open Ko-LLM Leaderboard	29.03	Average (%)	9.2
Open Korean LLM - KorNAT-Helpful	40.73	Normalized accuracy (%)	8.8
Open Korean LLM - Ko-Winogrande	51.93	Accuracy (%)	8
Open Korean LLM - KorNAT-CKA	11.37	Normalized accuracy (%)	2.4
Open Korean LLM - Ko-GSM8K (flexible extract)	0	Exact match, flexible extract (%)	2