llama-2-koen-13B-gangkk-alpaca-cosine-all-epoch3-merge: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1409 ± 17, rank #1832 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 | 26.36 | Normalized accuracy (%) | 63.9 |
| Open Korean LLM Leaderboard | 33.97 | Average Score (%) | 45.6 |
| Open Ko-LLM Leaderboard | 33.97 | Average (%) | 45.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.33 | Exact match, flexible extract (%) | 42.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - KorNAT-Helpful | 44.27 | Normalized accuracy (%) | 28.2 |
| Open Korean LLM - Ko-IFEval | 23.45 | Strict accuracy, prompt/instruction mean (%) | 27 |
| Open Korean LLM - KorNAT-Harmless | 61.23 | Normalized accuracy (%) | 25.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-koen-13b-gangkk-alpaca-cosine-all-epoch3-merge · How It Works · Data refreshed daily, snapshot 2026-09-19.