Llama-2-ko-DPO-13B: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1418 ± 17, rank #1771 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 50.8 | Normalized accuracy (%) | 87.2 |
| Open Korean LLM - Ko-Winogrande | 65.43 | Accuracy (%) | 84.4 |
| Open Korean LLM - KorNAT-Harmless | 66.09 | Normalized accuracy (%) | 84.2 |
| Open Korean LLM - KorNAT-CKA | 26.45 | Normalized accuracy (%) | 64.5 |
| Open Korean LLM Leaderboard | 34.85 | Average Score (%) | 49 |
| Open Ko-LLM Leaderboard | 34.85 | Average (%) | 48.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.19 | Exact match, flexible extract (%) | 40.4 |
| Open Korean LLM - Ko-IFEval | 23.39 | Strict accuracy, prompt/instruction mean (%) | 26.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.69 | Normalized accuracy (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-ko-dpo-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.