practice-kullmmistral-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1377 ± 17, rank #2075 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 48.48 | Normalized accuracy (%) | 68.6 |
| Open Korean LLM - KorNAT-Harmless | 63.32 | Normalized accuracy (%) | 60.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 18.57 | Exact match, flexible extract (%) | 49.7 |
| Open Korean LLM - Ko-IFEval | 26.87 | Strict accuracy, prompt/instruction mean (%) | 40.8 |
| Open Korean LLM - Ko-Winogrande | 57.7 | Accuracy (%) | 33.8 |
| Open Korean LLM Leaderboard | 31.79 | Average Score (%) | 29.4 |
| Open Ko-LLM Leaderboard | 31.79 | Average (%) | 29.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - KorNAT-CKA | 18.23 | Normalized accuracy (%) | 18.5 |
Interactive version: theaggregate.ai/model?slug=practice-kullmmistral-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.