llama2-org-koen-7B: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1377 ± 17, rank #2074 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.22 | Accuracy (%) | 73 |
| Open Korean LLM - Ko-IFEval | 25.89 | Strict accuracy, prompt/instruction mean (%) | 37.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM Leaderboard | 32.19 | Average Score (%) | 31.6 |
| Open Ko-LLM Leaderboard | 32.19 | Average (%) | 31.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 6.52 | Exact match, flexible extract (%) | 28.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 43.18 | Normalized accuracy (%) | 21.8 |
| Open Korean LLM - KorNAT-CKA | 18.21 | Normalized accuracy (%) | 18.4 |
| Open Korean LLM - KorNAT-Harmless | 60.62 | Normalized accuracy (%) | 16.5 |
Interactive version: theaggregate.ai/model?slug=llama2-org-koen-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.