Llama 3 8B Instruct SkillMix: benchmark results
Provider: Meta.
Aggregate Rating 1456 ± 43, rank #3520 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AlpacaEval 2.0 | 42.76 | LC Win Rate (%) | 82.9 |
| Open Persian LLM - AUT Multiple Choice Persian | 54.04 | Accuracy (%) | 60 |
| Open Persian LLM - MMLU Pro | 23.38 | Accuracy (%) | 53.3 |
| Open Persian LLM - Part Multiple Choice | 34.67 | Accuracy (%) | 46.7 |
| Open Persian LLM Leaderboard | 49.09 | Average Score (%) | 46.7 |
| Open Persian LLM - ARC Challenge | 60.4 | Accuracy (%) | 41.7 |
| Open Persian LLM - ARC Easy | 72.98 | Accuracy (%) | 36.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-skillmix · How It Works · Data refreshed daily, snapshot 2026-11-08.