Dorna-Llama3-8B-Instruct: benchmark results
Provider: Other.
Aggregate Rating 1418 ± 40, rank #5244 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Persian LLM - MMLU Pro | 23.39 | Accuracy (%) | 56.7 |
| Open Persian LLM - ARC Challenge | 61.07 | Accuracy (%) | 46.7 |
| Open Persian LLM - AUT Multiple Choice Persian | 52.86 | Accuracy (%) | 45 |
| Open Persian LLM Leaderboard | 48.32 | Average Score (%) | 33.3 |
| Open Persian LLM - Part Multiple Choice | 33.88 | Accuracy (%) | 26.7 |
| Open Persian LLM - ARC Easy | 70.4 | Accuracy (%) | 20 |
Interactive version: theaggregate.ai/model?slug=dorna-llama3-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.