Korean-OpenOrca-13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1353 ± 17, rank #2218 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.64 | Accuracy (%) | 79.8 |
| Open Korean LLM - KorNAT-Harmless | 62.58 | Normalized accuracy (%) | 46.5 |
| Open Korean LLM - KorNAT-CKA | 22.17 | Normalized accuracy (%) | 38.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.99 | Exact match, flexible extract (%) | 35.4 |
| Open Korean LLM - KorNAT-Helpful | 44.15 | Normalized accuracy (%) | 27.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Ko-LLM Leaderboard | 30.4 | Average (%) | 19 |
| Open Korean LLM Leaderboard | 30.4 | Average Score (%) | 19 |
| Open Korean LLM - Ko-IFEval | 4.14 | Strict accuracy, prompt/instruction mean (%) | 5.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.69 | Normalized accuracy (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=korean-openorca-13b · How It Works · Data refreshed daily, snapshot 2026-09-19.