kor-llama2-13B-dpo: benchmark results
Provider: Other. Access: Open.
Unified ELO 1397 ± 17, rank #1935 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 63.48 | Normalized accuracy (%) | 63.4 |
| Open Korean LLM - Ko-EQ-Bench | 10.29 | EQ-Bench score | 56.5 |
| Open Korean LLM - KorNAT-CKA | 23.07 | Normalized accuracy (%) | 42.3 |
| Open Korean LLM - Ko-Winogrande | 58.8 | Accuracy (%) | 41.4 |
| Open Korean LLM Leaderboard | 33.24 | Average Score (%) | 40 |
| Open Ko-LLM Leaderboard | 33.24 | Average (%) | 39.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.16 | Exact match, flexible extract (%) | 33.8 |
| Open Korean LLM - Ko-IFEval | 23.45 | Strict accuracy, prompt/instruction mean (%) | 27 |
| Open Korean LLM - KorNAT-Helpful | 43.3 | Normalized accuracy (%) | 22.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=kor-llama2-13b-dpo · How It Works · Data refreshed daily, snapshot 2026-09-19.