ko-Meta-Llama-3.1-8B-Instruct: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1423 ± 43, rank #5182 of 10552 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-GSM8K (flexible extract)54.21Exact match, flexible extract (%)88.2
Open Korean LLM - Ko-IFEval40.1Strict accuracy, prompt/instruction mean (%)81.8
Open Korean LLM - Ko-EQ-Bench27.44EQ-Bench score74.6
Open Korean LLM - KorNAT-Harmless64.35Normalized accuracy (%)73.2
Open Korean LLM Leaderboard38.19Average Score (%)65
Open Korean LLM - Ko-GPQA-Diamond23.74Normalized accuracy (%)55.6
Open Korean LLM - KorNAT-Helpful46.08Normalized accuracy (%)42.1
Open Korean LLM - KorNAT-CKA21.92Normalized accuracy (%)37.4
Open Korean LLM - Ko-Winogrande56.83Accuracy (%)28

Interactive version: theaggregate.ai/model?slug=ko-meta-llama-3-1-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-16.