minillama3.8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1381 ± 17, rank #2040 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.43 | Normalized accuracy (%) | 79.4 |
| Open Korean LLM - KorNAT-Harmless | 64.17 | Normalized accuracy (%) | 71.3 |
| Open Korean LLM - KorNAT-CKA | 25.22 | Normalized accuracy (%) | 55.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-EQ-Bench | 0.62 | EQ-Bench score | 46.1 |
| Open Korean LLM Leaderboard | 32.14 | Average Score (%) | 31.2 |
| Open Ko-LLM Leaderboard | 32.14 | Average (%) | 31 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 8.04 | Exact match, flexible extract (%) | 30.9 |
| Open Korean LLM - Ko-IFEval | 21.1 | Strict accuracy, prompt/instruction mean (%) | 20.3 |
| Open Korean LLM - Ko-Winogrande | 55.33 | Accuracy (%) | 19.7 |
Interactive version: theaggregate.ai/model?slug=minillama3-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.