kullm-mistral: benchmark results
Provider: Korea University. Access: Open.
Unified ELO 1289 ± 18, rank #2483 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 28.79 | Normalized accuracy (%) | 98.1 |
| Open Korean LLM - KorNAT-Harmless | 61.43 | Normalized accuracy (%) | 28.4 |
| Open Korean LLM - Ko-IFEval | 23.69 | Strict accuracy, prompt/instruction mean (%) | 28.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.27 | Exact match, flexible extract (%) | 18.5 |
| Open Korean LLM - KorNAT-Helpful | 41.93 | Normalized accuracy (%) | 14.2 |
| Open Korean LLM - Ko-Winogrande | 52.33 | Accuracy (%) | 8.8 |
| Open Ko-LLM Leaderboard | 27.97 | Average (%) | 3.7 |
| Open Korean LLM Leaderboard | 27.97 | Average Score (%) | 3.7 |
| Open Korean LLM - KorNAT-CKA | 9.39 | Normalized accuracy (%) | 1.6 |
Interactive version: theaggregate.ai/model?slug=kullm-mistral · How It Works · Data refreshed daily, snapshot 2026-09-19.