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.

Aggregate Rating 1384 ± 30, rank #6737 of 10916 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-Winogrande	66.61	Accuracy (%)	88.8
Open LLM Leaderboard v1 - MMLU	64.83	Accuracy (%) (5-shot)	77.2
Open Korean LLM - KorNAT-Helpful	49.13	Normalized accuracy (%)	76.7
Open LLM Leaderboard v1 - WinoGrande	79.08	Accuracy (%) (5-shot)	67.2
Open Korean LLM - KorNAT-Harmless	62.92	Normalized accuracy (%)	52
Open LLM Leaderboard v1 - GSM8K	32.22	Accuracy (%) (5-shot)	48.7
Open LLM Leaderboard v1 - HellaSwag	81.26	Normalized accuracy (%) (10-shot)	44.3
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 LLM Leaderboard v1 - ARC Challenge	58.45	Normalized accuracy (%) (25-shot)	39.8
Open Korean LLM Leaderboard	33	Average Score (%)	36.9
Open Korean LLM - Ko-IFEval	23.91	Strict accuracy, prompt/instruction mean (%)	29