Configurable-Mistral-7B: benchmark results
Provider: Other. Released 2024-06-11. Access: Open.
Aggregate Rating 1376 ± 18, rank #1313 of 1656 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 67.05 | Normalized accuracy (%) | 87.8 |
| Open Chinese LLM - TruthfulQA MC | 59.51 | Accuracy (%) | 81.7 |
| Open Korean LLM - Ko-IFEval | 37.34 | Strict accuracy, prompt/instruction mean (%) | 78 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - KorNAT-CKA | 26.03 | Normalized accuracy (%) | 61.7 |
| Open Portuguese LLM - ASSIN2 RTE | 90.89 | Macro F1 (%) | 61.1 |
| Open Portuguese LLM - FaQuAD NLI | 68.22 | Macro F1 (%) | 56.3 |
| Open Korean LLM - Ko-EQ-Bench | 9.1 | EQ-Bench score | 55.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 19.79 | Exact match, flexible extract (%) | 51.4 |
| Open Korean LLM Leaderboard | 35.29 | Average Score (%) | 51 |
| Open Ko-LLM Leaderboard | 35.29 | Average (%) | 50.9 |
| Open Korean LLM - KorNAT-Helpful | 46.83 | Normalized accuracy (%) | 49.7 |
Interactive version: theaggregate.ai/model?slug=configurable-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-10-20.