llama-3-Korean-8B-r-v1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1437 ± 17, rank #1619 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.38 | Exact match, flexible extract (%) | 71.5 |
| Open Korean LLM - Ko-IFEval | 33.84 | Strict accuracy, prompt/instruction mean (%) | 68.9 |
| Open Korean LLM - KorNAT-Helpful | 48.48 | Normalized accuracy (%) | 68.6 |
| Open Korean LLM Leaderboard | 36.72 | Average Score (%) | 58.5 |
| Open Ko-LLM Leaderboard | 36.72 | Average (%) | 58.4 |
| Open Korean LLM - KorNAT-CKA | 25 | Normalized accuracy (%) | 54.4 |
| Open Korean LLM - Ko-EQ-Bench | 2.36 | EQ-Bench score | 48.5 |
| Open Korean LLM - KorNAT-Harmless | 62.11 | Normalized accuracy (%) | 38.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - Ko-Winogrande | 56.75 | Accuracy (%) | 27.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-korean-8b-r-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.