llama-3-Korean-8B-r-v2: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1436 ± 17, rank #1625 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 36.32 | Exact match, flexible extract (%) | 69.9 |
| Open Korean LLM - Ko-IFEval | 32.44 | Strict accuracy, prompt/instruction mean (%) | 62.5 |
| Open Korean LLM - KorNAT-Helpful | 47.93 | Normalized accuracy (%) | 62.5 |
| Open Ko-LLM Leaderboard | 36.58 | Average (%) | 58 |
| Open Korean LLM Leaderboard | 36.58 | Average Score (%) | 58 |
| Open Korean LLM - Ko-EQ-Bench | 5.45 | EQ-Bench score | 51.2 |
| Open Korean LLM - KorNAT-CKA | 24.22 | Normalized accuracy (%) | 50.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - KorNAT-Harmless | 62.18 | Normalized accuracy (%) | 39.7 |
| Open Korean LLM - Ko-Winogrande | 56.91 | Accuracy (%) | 28.5 |
Interactive version: theaggregate.ai/model?slug=llama-3-korean-8b-r-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.