llama2-ko-chang-13B-instruct-chat: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1414 ± 17, rank #1803 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.88 | Accuracy (%) | 81.2 |
| Open Korean LLM - KorNAT-Helpful | 47.93 | Normalized accuracy (%) | 62.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 19.18 | Exact match, flexible extract (%) | 50.5 |
| Open Korean LLM - Ko-IFEval | 28.59 | Strict accuracy, prompt/instruction mean (%) | 48.8 |
| Open Korean LLM Leaderboard | 34.54 | Average Score (%) | 48.3 |
| Open Ko-LLM Leaderboard | 34.54 | Average (%) | 48.1 |
| Open Korean LLM - Ko-EQ-Bench | 0.56 | EQ-Bench score | 45.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - KorNAT-Harmless | 61.51 | Normalized accuracy (%) | 30.2 |
| Open Korean LLM - KorNAT-CKA | 17.98 | Normalized accuracy (%) | 17.3 |
Interactive version: theaggregate.ai/model?slug=llama2-ko-chang-13b-instruct-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.