Dorna2-Llama3.1-8B-Instruct: benchmark results
Provider: Other.
Aggregate Rating 1439 ± 38, rank #4228 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Persian LLM - ARC Easy | 79.59 | Accuracy (%) | 63.3 |
| Open Persian LLM Leaderboard | 50.72 | Average Score (%) | 60 |
| Open Persian LLM - ARC Challenge | 64.42 | Accuracy (%) | 56.7 |
| Open Persian LLM - AUT Multiple Choice Persian | 53.64 | Accuracy (%) | 53.3 |
| Open Persian LLM - MMLU Pro | 21.47 | Accuracy (%) | 43.3 |
| Open Persian LLM - Part Multiple Choice | 34.48 | Accuracy (%) | 40 |
Interactive version: theaggregate.ai/model?slug=dorna2-llama3-1-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.