Llama-2-ko-OpenOrca-gugugo-13B: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1369 ± 17, rank #2119 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 61.64 | Accuracy (%) | 63.4 |
| Open Korean LLM - KorNAT-Helpful | 45.23 | Normalized accuracy (%) | 35.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.93 | Exact match, flexible extract (%) | 33.6 |
| Open Korean LLM - Ko-IFEval | 24.84 | Strict accuracy, prompt/instruction mean (%) | 31.5 |
| Open Korean LLM Leaderboard | 31.64 | Average Score (%) | 28.6 |
| Open Ko-LLM Leaderboard | 31.64 | Average (%) | 28.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - KorNAT-Harmless | 58.95 | Normalized accuracy (%) | 5 |
| Open Korean LLM - KorNAT-CKA | 13.68 | Normalized accuracy (%) | 4.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-ko-openorca-gugugo-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.