ko-llm-llama-2-7B-LoRA-IA3 Benchmark Results

ko-llm-llama-2-7B-LoRA-IA3: benchmark results

Provider: Other. Access: Open.

Unified ELO 1238 ± 18, rank #2588 of 2656 rated models, from 10 benchmark results.

Benchmark	Score	Metric	Percentile
Open Korean LLM - Ko-GPQA-Diamond	21.72	Normalized accuracy (%)	29.4
Open Korean LLM - Ko-EQ-Bench	0	EQ-Bench score	24.5
Open Korean LLM - KorNAT-Helpful	41.55	Normalized accuracy (%)	12.5
Open Korean LLM - KorNAT-CKA	15.78	Normalized accuracy (%)	10.7
Open Korean LLM - Ko-IFEval	15.29	Strict accuracy, prompt/instruction mean (%)	10.5
Open Korean LLM - Ko-GSM8K (flexible extract)	0.23	Exact match, flexible extract (%)	7.3
Open Korean LLM - Ko-Winogrande	50.28	Accuracy (%)	3.3
Open Ko-LLM Leaderboard	25.65	Average (%)	0.7
Open Korean LLM Leaderboard	25.65	Average Score (%)	0.7
Open Korean LLM - KorNAT-Harmless	51.74	Normalized accuracy (%)	0

Interactive version: theaggregate.ai/model?slug=ko-llm-llama-2-7b-lora-ia3 · How It Works · Data refreshed daily, snapshot 2026-09-19.