polyglot-5.8B-koalpaca-v1.1b_test3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1309 ± 17, rank #2424 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 17.64 | Normalized accuracy (%) | 15.5 |
| Open Korean LLM - KorNAT-Harmless | 60.49 | Normalized accuracy (%) | 15.2 |
| Open Korean LLM - Ko-IFEval | 18.27 | Strict accuracy, prompt/instruction mean (%) | 13.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.83 | Exact match, flexible extract (%) | 10.8 |
| Open Korean LLM Leaderboard | 28.89 | Average Score (%) | 8.5 |
| Open Ko-LLM Leaderboard | 28.89 | Average (%) | 8.4 |
| Open Korean LLM - Ko-Winogrande | 50.36 | Accuracy (%) | 3.6 |
| Open Korean LLM - KorNAT-Helpful | 38.15 | Normalized accuracy (%) | 3.1 |
Interactive version: theaggregate.ai/model?slug=polyglot-5-8b-koalpaca-v1-1b-test3 · How It Works · Data refreshed daily, snapshot 2026-09-19.