EEVE-Korean-10.8B-SFT-v0.1: benchmark results
Provider: Yanolja. Access: Open.
Unified ELO 1290 ± 17, rank #2480 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Helpful | 41.38 | Normalized accuracy (%) | 11.6 |
| Open Korean LLM - Ko-IFEval | 16.07 | Strict accuracy, prompt/instruction mean (%) | 11.1 |
| Open Korean LLM - KorNAT-Harmless | 59.95 | Normalized accuracy (%) | 10.7 |
| Open Korean LLM Leaderboard | 28.2 | Average Score (%) | 5.5 |
| Open Ko-LLM Leaderboard | 28.2 | Average (%) | 5.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.08 | Exact match, flexible extract (%) | 4.8 |
| Open Korean LLM - KorNAT-CKA | 10.97 | Normalized accuracy (%) | 2.2 |
| Open Korean LLM - Ko-Winogrande | 47.12 | Accuracy (%) | 0 |
Interactive version: theaggregate.ai/model?slug=eeve-korean-10-8b-sft-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.