Llama3-beomi-Open-Ko-8B-Instruct-preview-test6: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1338 ± 17, rank #2297 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.78 | Normalized accuracy (%) | 95 |
| Open Korean LLM - KorNAT-CKA | 28.99 | Normalized accuracy (%) | 78.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 20.39 | Strict accuracy, prompt/instruction mean (%) | 18.8 |
| Open Korean LLM Leaderboard | 30.05 | Average Score (%) | 16.6 |
| Open Ko-LLM Leaderboard | 30.05 | Average (%) | 16.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.06 | Exact match, flexible extract (%) | 12.1 |
| Open Korean LLM - Ko-Winogrande | 53.04 | Accuracy (%) | 11.5 |
| Open Korean LLM - KorNAT-Helpful | 38.5 | Normalized accuracy (%) | 3.7 |
| Open Korean LLM - KorNAT-Harmless | 58.09 | Normalized accuracy (%) | 2.4 |
Interactive version: theaggregate.ai/model?slug=llama3-beomi-open-ko-8b-instruct-preview-test6 · How It Works · Data refreshed daily, snapshot 2026-09-19.