llama-2-ko-7B-pt Benchmark Results

llama-2-ko-7B-pt: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1262 ± 18, rank #2556 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	29.29	Normalized accuracy (%)	99.2
Open Korean LLM - KorNAT-CKA	20.07	Normalized accuracy (%)	28
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-Winogrande	53.43	Accuracy (%)	12.6
Open Korean LLM - KorNAT-Helpful	40.92	Normalized accuracy (%)	9.4
Open Korean LLM - Ko-IFEval	6.97	Strict accuracy, prompt/instruction mean (%)	6.7
Open Korean LLM - KorNAT-Harmless	59.35	Normalized accuracy (%)	5.9
Open Korean LLM - Ko-GSM8K (flexible extract)	0	Exact match, flexible extract (%)	2
Open Ko-LLM Leaderboard	27.09	Average (%)	1.6
Open Korean LLM Leaderboard	27.09	Average Score (%)	1.6

Interactive version: theaggregate.ai/model?slug=llama-2-ko-7b-pt · How It Works · Data refreshed daily, snapshot 2026-09-19.