Llama-3-Instruct-8B-SLiC-HF: benchmark results
Princeton NLP's SLiC-HF preference-tuned Llama 3 8B Instruct, released as a baseline from the SimPO paper. Provider: Princeton NLP. Released 2024-07-06. Access: Open.
Aggregate Rating 1452 ± 19, rank #994 of 1661 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 45.45 | Strict accuracy, prompt/instruction mean (%) | 89.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open LLM Leaderboard - IFEval | 74 | Score | 88.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 52.92 | Exact match, flexible extract (%) | 86.6 |
| Open Korean LLM - Ko-EQ-Bench | 35.63 | EQ-Bench score | 85.7 |
| Open Korean LLM Leaderboard | 41.68 | Average Score (%) | 83.3 |
| Open Ko-LLM Leaderboard | 41.68 | Average (%) | 83.2 |
| Open Portuguese LLM - FaQuAD NLI | 74.77 | Macro F1 (%) | 71.1 |
| Open Portuguese LLM - OAB Exams | 48.25 | Accuracy (%) | 68.9 |
| Open Portuguese LLM - ENEM | 67.39 | Accuracy (%) | 66.6 |
| Open Portuguese LLM - BLUEX | 55.49 | Accuracy (%) | 63.4 |
| Open Portuguese LLM - ASSIN2 RTE | 90.79 | Macro F1 (%) | 60.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-slic-hf · How It Works · Data refreshed daily, snapshot 2026-10-23.