Mistral-7B-ko-Y24-DPO_v0.1: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1312 ± 18, rank #2413 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 8.95 | Exact match, flexible extract (%) | 31.8 |
| Open Korean LLM - KorNAT-CKA | 20.71 | Normalized accuracy (%) | 30.8 |
| Open Korean LLM - KorNAT-Harmless | 61.54 | Normalized accuracy (%) | 30.7 |
| Open Korean LLM - Ko-Winogrande | 55.96 | Accuracy (%) | 23.7 |
| Open Korean LLM - KorNAT-Helpful | 42.6 | Normalized accuracy (%) | 17.6 |
| Open Korean LLM - Ko-IFEval | 13.84 | Strict accuracy, prompt/instruction mean (%) | 9.6 |
| Open Ko-LLM Leaderboard | 28.21 | Average (%) | 5.6 |
| Open Korean LLM Leaderboard | 28.21 | Average Score (%) | 5.6 |
| Open Korean LLM - Ko-EQ-Bench | -0.68 | EQ-Bench score | 4.3 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-ko-y24-dpo-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.