llama-2-koen-13B-mixed-v7: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1392 ± 17, rank #1967 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.77 | Accuracy (%) | 75.7 |
| Open Korean LLM - KorNAT-CKA | 23.24 | Normalized accuracy (%) | 43.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.65 | Exact match, flexible extract (%) | 41.5 |
| Open Korean LLM Leaderboard | 33.03 | Average Score (%) | 37.6 |
| Open Ko-LLM Leaderboard | 33.03 | Average (%) | 37.4 |
| Open Korean LLM - KorNAT-Harmless | 61.78 | Normalized accuracy (%) | 33.9 |
| Open Korean LLM - KorNAT-Helpful | 44.27 | Normalized accuracy (%) | 28.2 |
| Open Korean LLM - Ko-IFEval | 20 | Strict accuracy, prompt/instruction mean (%) | 17.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - Ko-EQ-Bench | -0.29 | EQ-Bench score | 5.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-mixed-v7 · How It Works · Data refreshed daily, snapshot 2026-09-19.