Llama-3-Open-Ko-8B-Instruct-seongi-KU: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1409 ± 17, rank #1831 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - KorNAT-CKA | 26.9 | Normalized accuracy (%) | 67.2 |
| Open Korean LLM - KorNAT-Harmless | 63.55 | Normalized accuracy (%) | 64.1 |
| Open Korean LLM - Ko-EQ-Bench | 6.23 | EQ-Bench score | 51.8 |
| Open Korean LLM - KorNAT-Helpful | 46.98 | Normalized accuracy (%) | 51.3 |
| Open Korean LLM - Ko-IFEval | 28.83 | Strict accuracy, prompt/instruction mean (%) | 50 |
| Open Korean LLM Leaderboard | 33.87 | Average Score (%) | 45 |
| Open Ko-LLM Leaderboard | 33.87 | Average (%) | 44.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.78 | Exact match, flexible extract (%) | 33.3 |
| Open Korean LLM - Ko-Winogrande | 54.62 | Accuracy (%) | 16.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-open-ko-8b-instruct-seongi-ku · How It Works · Data refreshed daily, snapshot 2026-09-19.