Llama-3-Instruct-8B-SLiC-HF-v0.2: benchmark results
Princeton NLP's Llama-3-Instruct-8B-SLiC-HF-v0.2, a Llama 3 8B 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 1462 ± 21, rank #925 of 1654 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 45.52 | Strict accuracy, prompt/instruction mean (%) | 89.6 |
| Open Korean LLM Leaderboard | 43.59 | Average Score (%) | 88.2 |
| Open Korean LLM - Ko-EQ-Bench | 35.18 | EQ-Bench score | 85.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 51.33 | Exact match, flexible extract (%) | 84.9 |
| Open LLM Leaderboard - IFEval | 71.1 | Score | 84.3 |
| Open Portuguese LLM - ASSIN2 RTE | 92.44 | Macro F1 (%) | 79 |
| Open Korean LLM - KorNAT-Helpful | 49.03 | Normalized accuracy (%) | 75.9 |
| Open Portuguese LLM - BLUEX | 58.14 | Accuracy (%) | 72.1 |
| Open Portuguese LLM - OAB Exams | 49.16 | Accuracy (%) | 71.6 |
| Open Portuguese LLM - ENEM | 68.09 | Accuracy (%) | 68.7 |
| Open Korean LLM - KorNAT-CKA | 27.23 | Normalized accuracy (%) | 68.3 |
| Open Korean LLM - Ko-Winogrande | 61.64 | Accuracy (%) | 63.4 |
Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-slic-hf-v0-2 · How It Works · Data refreshed daily, snapshot 2026-10-24.