Mistral-7B-3data-merged: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1398 ± 17, rank #1920 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - KorNAT-Harmless | 63.88 | Normalized accuracy (%) | 67.8 |
| Open Korean LLM - KorNAT-Helpful | 47.23 | Normalized accuracy (%) | 54.2 |
| Open Korean LLM - Ko-EQ-Bench | 1.81 | EQ-Bench score | 47.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 15.85 | Exact match, flexible extract (%) | 45.7 |
| Open Korean LLM - KorNAT-CKA | 22.29 | Normalized accuracy (%) | 39.2 |
| Open Korean LLM Leaderboard | 33.17 | Average Score (%) | 39.2 |
| Open Ko-LLM Leaderboard | 33.17 | Average (%) | 39 |
| Open Korean LLM - Ko-Winogrande | 56.51 | Accuracy (%) | 26.8 |
| Open Korean LLM - Ko-IFEval | 21.34 | Strict accuracy, prompt/instruction mean (%) | 21 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-3data-merged · How It Works · Data refreshed daily, snapshot 2026-09-19.