llama-2-koen-13B-mixed-v9: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1395 ± 17, rank #1948 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 | 23.32 | Normalized accuracy (%) | 44.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.48 | Exact match, flexible extract (%) | 42.9 |
| Open Korean LLM Leaderboard | 33.12 | Average Score (%) | 38.4 |
| Open Ko-LLM Leaderboard | 33.12 | Average (%) | 38.2 |
| Open Korean LLM - KorNAT-Harmless | 61.86 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Helpful | 44.57 | Normalized accuracy (%) | 30.8 |
| Open Korean LLM - Ko-IFEval | 24.18 | Strict accuracy, prompt/instruction mean (%) | 29.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - Ko-EQ-Bench | -6.27 | EQ-Bench score | 2.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-mixed-v9 · How It Works · Data refreshed daily, snapshot 2026-09-19.