llama3-eng-ko-8B-sl: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1431 ± 17, rank #1657 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 46.57 | Strict accuracy, prompt/instruction mean (%) | 91.4 |
| Open Korean LLM - KorNAT-Helpful | 49.95 | Normalized accuracy (%) | 83 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 26.38 | Exact match, flexible extract (%) | 60 |
| Open Ko-LLM Leaderboard | 36.38 | Average (%) | 56.9 |
| Open Korean LLM Leaderboard | 36.38 | Average Score (%) | 56.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-EQ-Bench | 1.66 | EQ-Bench score | 47.4 |
| Open Korean LLM - KorNAT-Harmless | 61.98 | Normalized accuracy (%) | 36.7 |
| Open Korean LLM - Ko-Winogrande | 56.83 | Accuracy (%) | 28 |
| Open Korean LLM - KorNAT-CKA | 18.19 | Normalized accuracy (%) | 18.3 |
Interactive version: theaggregate.ai/model?slug=llama3-eng-ko-8b-sl · How It Works · Data refreshed daily, snapshot 2026-09-19.