Mistral-instruct-DPO-Y24-v2: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1312 ± 26, rank #2414 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.83 | Normalized accuracy (%) | 77.2 |
| Open Korean LLM - Ko-Winogrande | 59.91 | Accuracy (%) | 49.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 15.85 | Exact match, flexible extract (%) | 45.7 |
| Open Korean LLM - KorNAT-Helpful | 45.75 | Normalized accuracy (%) | 39 |
| Open Korean LLM - KorNAT-CKA | 22.2 | Normalized accuracy (%) | 38.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - Ko-IFEval | 20.92 | Strict accuracy, prompt/instruction mean (%) | 20 |
| Open Korean LLM Leaderboard | 27.3 | Average Score (%) | 1.8 |
| Open Ko-LLM Leaderboard | 27.3 | Average (%) | 1.7 |
| Open Korean LLM - Ko-EQ-Bench | -35.21 | EQ-Bench score | 0.1 |
Interactive version: theaggregate.ai/model?slug=mistral-instruct-dpo-y24-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.