llama-2-ko-plain: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1273 ± 18, rank #2533 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - KorNAT-Harmless | 61.81 | Normalized accuracy (%) | 34.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 43.65 | Normalized accuracy (%) | 24.5 |
| Open Korean LLM - Ko-IFEval | 19.06 | Strict accuracy, prompt/instruction mean (%) | 15.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.45 | Exact match, flexible extract (%) | 8.7 |
| Open Korean LLM - Ko-Winogrande | 50.99 | Accuracy (%) | 5.1 |
| Open Korean LLM Leaderboard | 27.62 | Average Score (%) | 2.6 |
| Open Ko-LLM Leaderboard | 27.62 | Average (%) | 2.5 |
| Open Korean LLM - KorNAT-CKA | 6.57 | Normalized accuracy (%) | 0.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-ko-plain · How It Works · Data refreshed daily, snapshot 2026-09-19.