koquality-polyglot-ko-12.8B-inst: benchmark results
Provider: Other. Access: Open.
Unified ELO 1377 ± 17, rank #2072 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - KorNAT-CKA | 27.38 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-Winogrande | 58.41 | Accuracy (%) | 38.4 |
| Open Korean LLM - KorNAT-Helpful | 44.77 | Normalized accuracy (%) | 32.5 |
| Open Korean LLM Leaderboard | 32.19 | Average Score (%) | 31.6 |
| Open Ko-LLM Leaderboard | 32.19 | Average (%) | 31.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.94 | Normalized accuracy (%) | 21.1 |
| Open Korean LLM - Ko-IFEval | 20.2 | Strict accuracy, prompt/instruction mean (%) | 18.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.83 | Exact match, flexible extract (%) | 10.8 |
Interactive version: theaggregate.ai/model?slug=koquality-polyglot-ko-12-8b-inst · How It Works · Data refreshed daily, snapshot 2026-09-19.