Open Persian LLM - AUT Multiple Choice Persian — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 31 models tracked.

Top models

#ModelScore
1Llama 3.3 70B Instruct71.4
2Gemma 3 27B (IT)64.3
3Gemma 2 27B (IT)63.12
4Gemma 2 9B (IT)62.33
5aya-expanse-32B62.33
6Qwen 2.5 32B Instruct61.34
7aya-23-35B61.14
8QwQ 32B-Preview60.15
9aya-expanse-8B58.38
10Gemma 3 12B (IT)57
11Llama 3.1 8B Instruct54.24
12Llama 3 8B Instruct53.85
13Llama 3.1 8B53.45
14aya-23-8B52.86
15Qwen 2.5 7B Instruct52.66

Interactive version: theaggregate.ai/benchmark?slug=open-persian-llm-aut-multiple-choice-persian · How the rankings work · Data refreshed daily, snapshot 2026-07-22.