penguin3.1.6n-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1361 ± 17, rank #2166 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 23.25 | Normalized accuracy (%) | 43.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 13.57 | Exact match, flexible extract (%) | 41.4 |
| Open Korean LLM - Ko-IFEval | 22.92 | Strict accuracy, prompt/instruction mean (%) | 25 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM Leaderboard | 30.95 | Average Score (%) | 23.2 |
| Open Ko-LLM Leaderboard | 30.95 | Average (%) | 23.1 |
| Open Korean LLM - Ko-Winogrande | 55.41 | Accuracy (%) | 20.1 |
| Open Korean LLM - KorNAT-Helpful | 42.52 | Normalized accuracy (%) | 17 |
| Open Korean LLM - KorNAT-Harmless | 58.8 | Normalized accuracy (%) | 4.5 |
Interactive version: theaggregate.ai/model?slug=penguin3-1-6n-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.