freeze_KoSoLAR-10.7B-v0.2.1.4_dedup Benchmark Results

freeze_KoSoLAR-10.7B-v0.2.1.4_dedup: benchmark results

Provider: Other. Access: Open.

Unified ELO 1389 ± 18, rank #1983 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-Winogrande	66.61	Accuracy (%)	88.8
Open Korean LLM - KorNAT-Helpful	49.12	Normalized accuracy (%)	76.7
Open Korean LLM - KorNAT-Harmless	62.92	Normalized accuracy (%)	51.9
Open Korean LLM - Ko-EQ-Bench	0.16	EQ-Bench score	43.7
Open Korean LLM - KorNAT-CKA	22.6	Normalized accuracy (%)	40.4
Open Korean LLM Leaderboard	33	Average Score (%)	37.2
Open Ko-LLM Leaderboard	33	Average (%)	36.9
Open Korean LLM - Ko-IFEval	23.91	Strict accuracy, prompt/instruction mean (%)	29
Open Korean LLM - Ko-GPQA-Diamond	20.71	Normalized accuracy (%)	18.8
Open Korean LLM - Ko-GSM8K (flexible extract)	0.08	Exact match, flexible extract (%)	4.8