Mistral-7B-OP-u1k-ver0.7: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1408 ± 17, rank #1844 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 - Ko-GSM8K (flexible extract) | 23.28 | Exact match, flexible extract (%) | 56.3 |
| Open Korean LLM - KorNAT-Harmless | 62.95 | Normalized accuracy (%) | 52.3 |
| Open Korean LLM Leaderboard | 34.18 | Average Score (%) | 46.5 |
| Open Ko-LLM Leaderboard | 34.18 | Average (%) | 46.4 |
| Open Korean LLM - Ko-Winogrande | 58.64 | Accuracy (%) | 40.3 |
| Open Korean LLM - Ko-IFEval | 26.41 | Strict accuracy, prompt/instruction mean (%) | 38.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 19.06 | Normalized accuracy (%) | 22.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-op-u1k-ver0-7 · How It Works · Data refreshed daily, snapshot 2026-09-19.