eeve-leaderboard-inst-v1.5: benchmark results
Provider: Yanolja. Access: Open.
Unified ELO 1460 ± 17, rank #1449 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 29.23 | Normalized accuracy (%) | 78.9 |
| Open Korean LLM - Ko-Winogrande | 63.46 | Accuracy (%) | 74.2 |
| Open Korean LLM Leaderboard | 38.84 | Average Score (%) | 68.8 |
| Open Ko-LLM Leaderboard | 38.84 | Average (%) | 68.6 |
| Open Korean LLM - Ko-EQ-Bench | 22.32 | EQ-Bench score | 67.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-Harmless | 62.41 | Normalized accuracy (%) | 43.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.1 | Exact match, flexible extract (%) | 42.4 |
| Open Korean LLM - KorNAT-Helpful | 44.4 | Normalized accuracy (%) | 29.5 |
| Open Korean LLM - Ko-IFEval | 20.26 | Strict accuracy, prompt/instruction mean (%) | 18.4 |
Interactive version: theaggregate.ai/model?slug=eeve-leaderboard-inst-v1-5 · How It Works · Data refreshed daily, snapshot 2026-09-19.