llama-2-koen-13B-mixed-v8: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1388 ± 17, rank #1995 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-Helpful | 45.42 | Normalized accuracy (%) | 36.6 |
| Open Korean LLM Leaderboard | 32.87 | Average Score (%) | 36.3 |
| Open Ko-LLM Leaderboard | 32.87 | Average (%) | 36.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.86 | Exact match, flexible extract (%) | 33.4 |
| Open Korean LLM - KorNAT-Harmless | 61.62 | Normalized accuracy (%) | 31.8 |
| Open Korean LLM - KorNAT-CKA | 20.21 | Normalized accuracy (%) | 28.9 |
| Open Korean LLM - Ko-IFEval | 23.08 | Strict accuracy, prompt/instruction mean (%) | 25.7 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-mixed-v8 · How It Works · Data refreshed daily, snapshot 2026-09-19.