test-llama2-ko-7B Benchmark Results

test-llama2-ko-7B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1294 ± 17, rank #2472 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	27.27	Normalized accuracy (%)	92.4
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - Ko-IFEval	17.19	Strict accuracy, prompt/instruction mean (%)	12.7
Open Korean LLM - KorNAT-CKA	16.2	Normalized accuracy (%)	11.8
Open Korean LLM - KorNAT-Helpful	41.35	Normalized accuracy (%)	11.5
Open Ko-LLM Leaderboard	28.33	Average (%)	5.9
Open Korean LLM Leaderboard	28.33	Average Score (%)	5.9
Open Korean LLM - Ko-Winogrande	50.43	Accuracy (%)	3.8
Open Korean LLM - Ko-GSM8K (flexible extract)	0	Exact match, flexible extract (%)	2
Open Korean LLM - KorNAT-Harmless	52.71	Normalized accuracy (%)	0.2

Interactive version: theaggregate.ai/model?slug=test-llama2-ko-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.