KULLM-RLHF: benchmark results
Provider: Korea University. Access: Open.
Unified ELO 1395 ± 18, rank #1946 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 | 27.63 | Normalized accuracy (%) | 70.9 |
| Open Korean LLM - Ko-IFEval | 27.67 | Strict accuracy, prompt/instruction mean (%) | 44.4 |
| Open Korean LLM - KorNAT-Helpful | 46.3 | Normalized accuracy (%) | 44.4 |
| Open Korean LLM Leaderboard | 33.21 | Average Score (%) | 39.6 |
| Open Ko-LLM Leaderboard | 33.21 | Average (%) | 39.3 |
| Open Korean LLM - Ko-Winogrande | 58.17 | Accuracy (%) | 36.9 |
| Open Korean LLM - KorNAT-Harmless | 61.3 | Normalized accuracy (%) | 26.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.23 | Exact match, flexible extract (%) | 7.3 |
Interactive version: theaggregate.ai/model?slug=kullm-rlhf · How It Works · Data refreshed daily, snapshot 2026-09-19.