Mistral-instruct-Y24-DPO: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1399 ± 17, rank #1916 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 48.35 | Normalized accuracy (%) | 67.3 |
| Open Korean LLM - Ko-Winogrande | 61.64 | Accuracy (%) | 63.4 |
| Open Korean LLM - Ko-IFEval | 29.12 | Strict accuracy, prompt/instruction mean (%) | 50.5 |
| Open Korean LLM - KorNAT-Harmless | 62.63 | Normalized accuracy (%) | 47.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 16.83 | Exact match, flexible extract (%) | 47.3 |
| Open Korean LLM Leaderboard | 33.32 | Average Score (%) | 41.1 |
| Open Ko-LLM Leaderboard | 33.32 | Average (%) | 41 |
| 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 | 14.16 | Normalized accuracy (%) | 5.6 |
Interactive version: theaggregate.ai/model?slug=mistral-instruct-y24-dpo · How It Works · Data refreshed daily, snapshot 2026-09-19.