llama-3-Korean-8B-r-v-0.1: benchmark results
Provider: Meta. Released 2024-07-18. Access: Open.
Aggregate Rating 1398 ± 41, rank #6180 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 42.68 | Exact match, flexible extract (%) | 78 |
| Open Korean LLM - Ko-IFEval | 34.13 | Strict accuracy, prompt/instruction mean (%) | 69.9 |
| Open Korean LLM Leaderboard | 38.67 | Average Score (%) | 67.7 |
| Open LLM Leaderboard - IFEval | 49.16 | Score | 57.4 |
| Open Korean LLM - KorNAT-Harmless | 63.1 | Normalized accuracy (%) | 55.9 |
| Open Korean LLM - Ko-EQ-Bench | 7.6 | EQ-Bench score | 53.8 |
| Open Korean LLM - KorNAT-CKA | 24.17 | Normalized accuracy (%) | 49.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-Helpful | 46.55 | Normalized accuracy (%) | 47.4 |
| Open LLM Leaderboard - MMLU-Pro | 32.6 | Score | 44.9 |
| Open LLM Leaderboard - MATH Level 5 | 8.61 | Score | 43 |
| Open LLM Leaderboard - BBH | 48.06 | Score | 41.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-korean-8b-r-v-0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.