llama-2-koen-13B-dpo-v1: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1391 ± 17, rank #1976 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.85 | Accuracy (%) | 76.2 |
| Open Korean LLM - KorNAT-CKA | 23.25 | Normalized accuracy (%) | 43.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.42 | Exact match, flexible extract (%) | 41 |
| Open Korean LLM Leaderboard | 32.94 | Average Score (%) | 36.9 |
| Open Ko-LLM Leaderboard | 32.94 | Average (%) | 36.7 |
| Open Korean LLM - KorNAT-Harmless | 61.78 | Normalized accuracy (%) | 33.9 |
| Open Korean LLM - KorNAT-Helpful | 44.25 | Normalized accuracy (%) | 28.1 |
| Open Korean LLM - Ko-IFEval | 20 | Strict accuracy, prompt/instruction mean (%) | 17.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - Ko-EQ-Bench | -0.94 | EQ-Bench score | 4.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-dpo-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.