Mistral-7B-Base-SFT-SLiC-HF: benchmark results
Princeton NLP's Mistral-7B-Base-SFT-SLiC-HF, a Mistral 7B base model with SFT and SLiC-HF alignment, released alongside Princeton's SimPO preference-optimization paper. Provider: Princeton NLP. Released 2024-07-06. Access: Open.
Aggregate Rating 1386 ± 21, rank #1263 of 1654 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - Ko-IFEval | 40.27 | Strict accuracy, prompt/instruction mean (%) | 82.6 |
| Open LLM Leaderboard - MuSR | 42.61 | Score | 66.6 |
| Open Portuguese LLM - FaQuAD NLI | 71.82 | Macro F1 (%) | 64.4 |
| Open Korean LLM - Ko-EQ-Bench | 17 | EQ-Bench score | 62.7 |
| Open LLM Leaderboard - IFEval | 51.27 | Score | 61.2 |
| Open Korean LLM Leaderboard | 36.42 | Average Score (%) | 56.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 21.08 | Exact match, flexible extract (%) | 53.4 |
| Open Portuguese LLM - ASSIN2 RTE | 89.26 | Macro F1 (%) | 49.2 |
| Open LLM Leaderboard - GPQA | 29.19 | Score | 46.9 |
| Open Portuguese LLM - OAB Exams | 40.41 | Accuracy (%) | 44 |
| Open Portuguese LLM - BLUEX | 48.54 | Accuracy (%) | 42.6 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-base-sft-slic-hf · How It Works · Data refreshed daily, snapshot 2026-10-24.