EEVE-Korean-Instruct-10.8B-v1.0-Grade-Retrieval: benchmark results
Provider: Yanolja. Access: Open.
Unified ELO 1531 ± 17, rank #934 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 49.54 | EQ-Bench score | 95 |
| Open Korean LLM - Ko-Winogrande | 69.3 | Accuracy (%) | 94.7 |
| Open Korean LLM - KorNAT-CKA | 33.31 | Normalized accuracy (%) | 91.7 |
| Open Korean LLM Leaderboard | 44.75 | Average Score (%) | 90.8 |
| Open Ko-LLM Leaderboard | 44.75 | Average (%) | 90.7 |
| Open Korean LLM - Ko-IFEval | 42.03 | Strict accuracy, prompt/instruction mean (%) | 85.4 |
| Open Korean LLM - KorNAT-Harmless | 66.1 | Normalized accuracy (%) | 84.5 |
| Open Korean LLM - KorNAT-Helpful | 49.02 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 20.7 | Exact match, flexible extract (%) | 52.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
Interactive version: theaggregate.ai/model?slug=eeve-korean-instruct-10-8b-v1-0-grade-retrieval · How It Works · Data refreshed daily, snapshot 2026-09-19.