Custom-KoLLM-13B-v7: benchmark results
Provider: Other. Access: Open.
Unified ELO 1349 ± 17, rank #2242 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.4 | Accuracy (%) | 78.4 |
| Open Korean LLM - KorNAT-Helpful | 47.1 | Normalized accuracy (%) | 53.1 |
| Open Korean LLM - KorNAT-Harmless | 62.6 | Normalized accuracy (%) | 46.9 |
| Open Korean LLM - KorNAT-CKA | 19.64 | Normalized accuracy (%) | 25.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.73 | Exact match, flexible extract (%) | 19.9 |
| Open Korean LLM Leaderboard | 30.53 | Average Score (%) | 19.9 |
| Open Ko-LLM Leaderboard | 30.53 | Average (%) | 19.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - Ko-IFEval | 8.36 | Strict accuracy, prompt/instruction mean (%) | 7.3 |
Interactive version: theaggregate.ai/model?slug=custom-kollm-13b-v7 · How It Works · Data refreshed daily, snapshot 2026-09-19.