Mistral-7B-Instruct-SLiC-HF: benchmark results
Princeton NLP's Mistral-7B-Instruct-SLiC-HF, a Mistral 7B Instruct model aligned via SLiC-HF, released alongside Princeton's SimPO preference-optimization paper. Provider: Princeton NLP. Released 2024-07-06. Access: Open.
Aggregate Rating 1380 ± 19, rank #1298 of 1661 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 66.19 | Normalized accuracy (%) | 84.8 |
| Open Korean LLM - KorNAT-Helpful | 49.95 | Normalized accuracy (%) | 83 |
| Open Korean LLM - Ko-EQ-Bench | 28.29 | EQ-Bench score | 75.8 |
| Open Korean LLM - Ko-IFEval | 33.86 | Strict accuracy, prompt/instruction mean (%) | 69.1 |
| Open LLM Leaderboard - IFEval | 51.15 | Score | 61 |
| Open Portuguese LLM - ASSIN2 RTE | 90.44 | Macro F1 (%) | 57.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 23.81 | Exact match, flexible extract (%) | 57 |
| Open Korean LLM Leaderboard | 36.4 | Average Score (%) | 57 |
| Open Ko-LLM Leaderboard | 36.4 | Average (%) | 56.9 |
| Open Portuguese LLM - FaQuAD NLI | 66.4 | Macro F1 (%) | 52.3 |
| Open Portuguese LLM - BLUEX | 50.07 | Accuracy (%) | 46.5 |
| Open Portuguese LLM - ENEM | 59.27 | Accuracy (%) | 45.2 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-slic-hf · How It Works · Data refreshed daily, snapshot 2026-10-23.