test0_kullm-polyglot-5.8B-v2-koalpaca-v1.1B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1365 ± 18, rank #2140 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 26.31 | Normalized accuracy (%) | 63.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-IFEval | 27.86 | Strict accuracy, prompt/instruction mean (%) | 45.4 |
| Open Korean LLM Leaderboard | 31.5 | Average Score (%) | 27.9 |
| Open Ko-LLM Leaderboard | 31.5 | Average (%) | 27.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.41 | Accuracy (%) | 20.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.59 | Exact match, flexible extract (%) | 14.5 |
| Open Korean LLM - KorNAT-Harmless | 59.56 | Normalized accuracy (%) | 7.4 |
| Open Korean LLM - KorNAT-Helpful | 39.48 | Normalized accuracy (%) | 5.3 |
Interactive version: theaggregate.ai/model?slug=test0-kullm-polyglot-5-8b-v2-koalpaca-v1-1b · How It Works · Data refreshed daily, snapshot 2026-09-19.