EEVE-Korean_Instruct-10.8B-expo: benchmark results
Provider: Yanolja. Released 2024-07-12. Access: Open.
Unified ELO 1561 ± 17, rank #792 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 53.59 | EQ-Bench score | 96.3 |
| Open Ko-LLM Leaderboard | 47.99 | Average (%) | 95.5 |
| Open Korean LLM Leaderboard | 47.99 | Average Score (%) | 95.5 |
| Open Korean LLM - Ko-Winogrande | 69.38 | Accuracy (%) | 94.8 |
| Open Korean LLM - KorNAT-CKA | 34.34 | Normalized accuracy (%) | 93.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 51.18 | Exact match, flexible extract (%) | 84.7 |
| Open Korean LLM - KorNAT-Harmless | 65.88 | Normalized accuracy (%) | 83.4 |
| Open Korean LLM - Ko-IFEval | 37.55 | Strict accuracy, prompt/instruction mean (%) | 78.7 |
| Open Korean LLM - KorNAT-Helpful | 48.5 | Normalized accuracy (%) | 69.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
Interactive version: theaggregate.ai/model?slug=eeve-korean-instruct-10-8b-expo · How It Works · Data refreshed daily, snapshot 2026-09-19.