EEVE-Korean-Instruct-2.8B-v1.0: benchmark results
Provider: Yanolja.
Aggregate Rating 1340 ± 25, rank #7977 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 45.11 | Accuracy (%) (5-shot) | 59.2 |
| Open Korean LLM - Ko-EQ-Bench | 13.32 | EQ-Bench score | 59 |
| Open Korean LLM - Ko-IFEval | 27.27 | Strict accuracy, prompt/instruction mean (%) | 42.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.32 | MC2 (%) (0-shot) | 40.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.28 | Normalized accuracy (%) (25-shot) | 39.4 |
| Open LLM Leaderboard v1 - WinoGrande | 74.82 | Accuracy (%) (5-shot) | 38.9 |
| Open LLM Leaderboard v1 - MMLU | 53.35 | Accuracy (%) (5-shot) | 32.6 |
| Open Korean LLM Leaderboard | 32.29 | Average Score (%) | 32.3 |
| Open Korean LLM - KorNAT-Harmless | 61.52 | Normalized accuracy (%) | 30.5 |
| Open LLM Leaderboard v1 - HellaSwag | 72.42 | Normalized accuracy (%) (10-shot) | 22.8 |
| Open Korean LLM - KorNAT-Helpful | 43.23 | Normalized accuracy (%) | 22.4 |
Interactive version: theaggregate.ai/model?slug=eeve-korean-instruct-2-8b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.