EEVE_ver_4.1_sft: benchmark results
Provider: Yanolja. Access: Open.
Unified ELO 1478 ± 18, rank #1308 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 68.03 | Accuracy (%) | 92.4 |
| Open Korean LLM - KorNAT-CKA | 33.26 | Normalized accuracy (%) | 91.2 |
| Open Korean LLM - Ko-EQ-Bench | 37.96 | EQ-Bench score | 88.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 42.76 | Exact match, flexible extract (%) | 78.2 |
| Open Ko-LLM Leaderboard | 39.35 | Average (%) | 71.4 |
| Open Korean LLM Leaderboard | 39.35 | Average Score (%) | 71.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-IFEval | 26.7 | Strict accuracy, prompt/instruction mean (%) | 40 |
| Open Korean LLM - KorNAT-Harmless | 61.97 | Normalized accuracy (%) | 36.4 |
| Open Korean LLM - KorNAT-Helpful | 45.4 | Normalized accuracy (%) | 36.3 |
Interactive version: theaggregate.ai/model?slug=eeve-ver-4-1-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.