llama-2-koen-13B-OKI-v20231124-1e-5: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1393 ± 17, rank #1960 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.61 | Accuracy (%) | 75.1 |
| Open Korean LLM - KorNAT-Harmless | 64.27 | Normalized accuracy (%) | 72.1 |
| Open Korean LLM - KorNAT-Helpful | 47.67 | Normalized accuracy (%) | 58.7 |
| Open Korean LLM Leaderboard | 33.09 | Average Score (%) | 38.2 |
| Open Ko-LLM Leaderboard | 33.09 | Average (%) | 38 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.77 | Exact match, flexible extract (%) | 35.1 |
| Open Korean LLM - KorNAT-CKA | 20.11 | Normalized accuracy (%) | 28.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 20.9 | Strict accuracy, prompt/instruction mean (%) | 19.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-oki-v20231124-1e-5 · How It Works · Data refreshed daily, snapshot 2026-09-19.