llama-2-koen-13B-dpo-v2: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1396 ± 17, rank #1943 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.48 | Accuracy (%) | 79 |
| Open Korean LLM - KorNAT-CKA | 23.1 | Normalized accuracy (%) | 42.6 |
| Open Korean LLM - KorNAT-Harmless | 62.36 | Normalized accuracy (%) | 42.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.19 | Exact match, flexible extract (%) | 40.4 |
| Open Korean LLM Leaderboard | 33.15 | Average Score (%) | 38.8 |
| Open Ko-LLM Leaderboard | 33.15 | Average (%) | 38.5 |
| Open Korean LLM - KorNAT-Helpful | 44.57 | Normalized accuracy (%) | 30.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - Ko-IFEval | 20.82 | Strict accuracy, prompt/instruction mean (%) | 19.7 |
| Open Korean LLM - Ko-EQ-Bench | -2.51 | EQ-Bench score | 3.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-dpo-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.