koquality-polyglot-3.8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1350 ± 17, rank #2237 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 23.95 | Normalized accuracy (%) | 48.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - Ko-IFEval | 25.08 | Strict accuracy, prompt/instruction mean (%) | 33 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Ko-LLM Leaderboard | 30.78 | Average (%) | 21.5 |
| Open Korean LLM Leaderboard | 30.78 | Average Score (%) | 21.5 |
| Open Korean LLM - Ko-Winogrande | 55.09 | Accuracy (%) | 18.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.29 | Exact match, flexible extract (%) | 12.7 |
| Open Korean LLM - KorNAT-Helpful | 39.45 | Normalized accuracy (%) | 5.2 |
| Open Korean LLM - KorNAT-Harmless | 59.04 | Normalized accuracy (%) | 5.1 |
Interactive version: theaggregate.ai/model?slug=koquality-polyglot-3-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.