KoLlama-3-8B-Instruct: benchmark results
Provider: Other. Access: Open.
Unified ELO 1483 ± 17, rank #1250 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 45.77 | Strict accuracy, prompt/instruction mean (%) | 90.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 55.57 | Exact match, flexible extract (%) | 89.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - Ko-EQ-Bench | 33.44 | EQ-Bench score | 83.3 |
| Open Korean LLM Leaderboard | 40.05 | Average Score (%) | 75.2 |
| Open Ko-LLM Leaderboard | 40.05 | Average (%) | 75 |
| Open Korean LLM - KorNAT-CKA | 25.25 | Normalized accuracy (%) | 56.3 |
| Open Korean LLM - KorNAT-Helpful | 46.85 | Normalized accuracy (%) | 50 |
| Open Korean LLM - Ko-Winogrande | 58.33 | Accuracy (%) | 37.8 |
| Open Korean LLM - KorNAT-Harmless | 62.07 | Normalized accuracy (%) | 37.5 |
Interactive version: theaggregate.ai/model?slug=kollama-3-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.