Custom-KoLLM-13B-v1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1403 ± 17, rank #1887 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.38 | Accuracy (%) | 73.8 |
| Open Korean LLM - KorNAT-Helpful | 48.25 | Normalized accuracy (%) | 66.3 |
| Open Korean LLM - Ko-IFEval | 29.24 | Strict accuracy, prompt/instruction mean (%) | 50.7 |
| Open Korean LLM - KorNAT-Harmless | 62.8 | Normalized accuracy (%) | 50.5 |
| Open Korean LLM Leaderboard | 33.58 | Average Score (%) | 42.8 |
| Open Ko-LLM Leaderboard | 33.58 | Average (%) | 42.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 12.66 | Exact match, flexible extract (%) | 39.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 18.38 | Normalized accuracy (%) | 19.4 |
Interactive version: theaggregate.ai/model?slug=custom-kollm-13b-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.