mistralopithecus-v3-dpo-7B: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1483 ± 17, rank #1249 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 40.93 | Normalized accuracy (%) | 99.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - KorNAT-Helpful | 51.95 | Normalized accuracy (%) | 91.9 |
| Open Korean LLM - Ko-Winogrande | 63.85 | Accuracy (%) | 76.2 |
| Open Korean LLM - Ko-EQ-Bench | 28.02 | EQ-Bench score | 75.4 |
| Open Korean LLM Leaderboard | 40 | Average Score (%) | 74.7 |
| Open Ko-LLM Leaderboard | 40 | Average (%) | 74.6 |
| Open Korean LLM - Ko-IFEval | 33.74 | Strict accuracy, prompt/instruction mean (%) | 68.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 24.87 | Exact match, flexible extract (%) | 58.2 |
| Open Korean LLM - KorNAT-Harmless | 61.48 | Normalized accuracy (%) | 29.5 |
Interactive version: theaggregate.ai/model?slug=mistralopithecus-v3-dpo-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.