llama3-eng-ko-8B-sl5: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1472 ± 17, rank #1360 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 50.25 | Strict accuracy, prompt/instruction mean (%) | 93.6 |
| Open Korean LLM - KorNAT-Helpful | 51 | Normalized accuracy (%) | 88.5 |
| Open Korean LLM - Ko-EQ-Bench | 32.98 | EQ-Bench score | 82.5 |
| Open Korean LLM Leaderboard | 39.97 | Average Score (%) | 74.6 |
| Open Ko-LLM Leaderboard | 39.97 | Average (%) | 74.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 20.85 | Exact match, flexible extract (%) | 53 |
| Open Korean LLM - KorNAT-CKA | 20.21 | Normalized accuracy (%) | 28.9 |
| Open Korean LLM - Ko-Winogrande | 56.2 | Accuracy (%) | 25 |
| Open Korean LLM - KorNAT-Harmless | 61.06 | Normalized accuracy (%) | 22.3 |
Interactive version: theaggregate.ai/model?slug=llama3-eng-ko-8b-sl5 · How It Works · Data refreshed daily, snapshot 2026-09-19.