EEVE-Korean-10.8B-DPO-v1.0: benchmark results
Provider: Yanolja. Access: Open.
Unified ELO 1319 ± 18, rank #2392 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 30.3 | Normalized accuracy (%) | 99.8 |
| Open Korean LLM - KorNAT-Harmless | 62.68 | Normalized accuracy (%) | 48.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 41.7 | Normalized accuracy (%) | 13.5 |
| Open Korean LLM Leaderboard | 29.43 | Average Score (%) | 12 |
| Open Ko-LLM Leaderboard | 29.43 | Average (%) | 11.8 |
| Open Korean LLM - Ko-IFEval | 16.32 | Strict accuracy, prompt/instruction mean (%) | 11.6 |
| Open Korean LLM - Ko-Winogrande | 51.38 | Accuracy (%) | 6.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.15 | Exact match, flexible extract (%) | 6.3 |
| Open Korean LLM - KorNAT-CKA | 11.47 | Normalized accuracy (%) | 2.5 |
Interactive version: theaggregate.ai/model?slug=eeve-korean-10-8b-dpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.