Open Persian LLM - MMLU Pro — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 31 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.3 70B Instruct | 43.67 |
| 2 | Gemma 3 27B (IT) | 40.1 |
| 3 | Qwen 2.5 32B Instruct | 38.19 |
| 4 | QwQ 32B-Preview | 37.94 |
| 5 | Gemma 2 27B (IT) | 36.28 |
| 6 | Gemma 2 9B (IT) | 31.74 |
| 7 | aya-expanse-32B | 31.03 |
| 8 | Gemma 3 12B (IT) | 29.36 |
| 9 | Llama 3 8B Instruct | 25.54 |
| 10 | aya-23-35B | 25.54 |
| 11 | aya-expanse-8B | 25.06 |
| 12 | Llama 3.1 8B | 24.1 |
| 13 | Qwen 2 7B Instruct | 23.87 |
| 14 | Qwen 2.5 7B Instruct | 21.96 |
| 15 | suzume-llama-3-8B-multilingual | 21.95 |
Interactive version: theaggregate.ai/benchmark?slug=open-persian-llm-mmlu-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.