Llama 3 8B Ko Sft Dpo V1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1472 ± 17, rank #1361 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 47.31 | Exact match, flexible extract (%) | 81.2 |
| Open Korean LLM - Ko-IFEval | 37.29 | Strict accuracy, prompt/instruction mean (%) | 77.8 |
| Open Korean LLM - KorNAT-Harmless | 64.41 | Normalized accuracy (%) | 74 |
| Open Korean LLM - KorNAT-CKA | 27.95 | Normalized accuracy (%) | 72.8 |
| Open Korean LLM - Ko-EQ-Bench | 25.78 | EQ-Bench score | 72.1 |
| Open Ko-LLM Leaderboard | 39.24 | Average (%) | 70.6 |
| Open Korean LLM Leaderboard | 39.24 | Average Score (%) | 70.6 |
| Open Korean LLM - Ko-Winogrande | 61.4 | Accuracy (%) | 61.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-Helpful | 46.33 | Normalized accuracy (%) | 44.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-ko-sft-dpo-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.