KoRAE-13B-DPO: benchmark results
Provider: Other. Access: Open.
Unified ELO 1406 ± 17, rank #1859 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.69 | Accuracy (%) | 89.2 |
| Open Korean LLM - KorNAT-CKA | 31.89 | Normalized accuracy (%) | 88 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-IFEval | 29.3 | Strict accuracy, prompt/instruction mean (%) | 51.1 |
| Open Korean LLM Leaderboard | 33.62 | Average Score (%) | 43.3 |
| Open Ko-LLM Leaderboard | 33.62 | Average (%) | 43.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.16 | Exact match, flexible extract (%) | 33.8 |
| Open Korean LLM - KorNAT-Helpful | 44.12 | Normalized accuracy (%) | 27.4 |
| Open Korean LLM - KorNAT-Harmless | 60.89 | Normalized accuracy (%) | 20.2 |
| Open Korean LLM - Ko-EQ-Bench | -14.37 | EQ-Bench score | 1.6 |
Interactive version: theaggregate.ai/model?slug=korae-13b-dpo · How It Works · Data refreshed daily, snapshot 2026-09-19.