Open Persian LLM Leaderboard
Indexed results from Open Persian LLM Leaderboard. Each ranking retains its own metric and evaluation conditions.
AUT Multiple Choice Persian
openPersianLLM · Open Persian LLM Leaderboard · AUT Multiple Choice Persian · percent · Higher is better
ARC Easy
openPersianLLM · Open Persian LLM Leaderboard · ARC Easy · percent · Higher is better
Part Multiple Choice
openPersianLLM · Open Persian LLM Leaderboard · Part Multiple Choice · percent · Higher is better
- Meta: Llama 3.3 70B Instructmeta-llama51.42%
- Google: Gemma 3 27Bgoogle48.56%
- Qwen/QwQ-32B-Previewqwen46.64%
- Qwen/Qwen2.5-32B-Instructqwen46.06%
- Google: Gemma 2 27Bgoogle46.03%
- Google: Gemma 3 12Bgoogle43.52%
- google/gemma-2-9b-itgoogle42.7%
- Qwen: Qwen2.5 7B Instructqwen36.72%
- Qwen2-7B-Instructqwen35.9%
- Llama-3-1-8Bmeta-llama35.52%
- NousResearch/Hermes-3-Llama-3.1-8Bnousresearch35.01%
- meta-llama/Meta-Llama-3-8B-Instructmeta-llama34.99%
Part Multiple Choice
openPersianLLM · Open Persian LLM Leaderboard · Part Multiple Choice · percent · Higher is better
ARC Challenge
openPersianLLM · Open Persian LLM Leaderboard · ARC Challenge · percent · Higher is better
- Google: Gemma 3 27Bgoogle90.6%
- Meta: Llama 3.3 70B Instructmeta-llama89.93%
- Qwen/QwQ-32B-Previewqwen87.24%
- Google: Gemma 2 27Bgoogle85.91%
- Qwen/Qwen2.5-32B-Instructqwen85.91%
- google/gemma-2-9b-itgoogle84.56%
- Google: Gemma 3 12Bgoogle81.21%
- Qwen: Qwen2.5 7B Instructqwen69.13%
- Qwen2-7B-Instructqwen68.46%
- Google: Gemma 3 4Bgoogle63.76%
- NousResearch/Hermes-3-Llama-3.1-8Bnousresearch58.39%
- Gemma2-2b-itgoogle57.72%
MMLU Pro
openPersianLLM · Open Persian LLM Leaderboard · MMLU Pro · percent · Higher is better
MMLU Pro
openPersianLLM · Open Persian LLM Leaderboard · MMLU Pro · percent · Higher is better
- Meta: Llama 3.3 70B Instructmeta-llama43.67%
- Google: Gemma 3 27Bgoogle40.1%
- Qwen/Qwen2.5-32B-Instructqwen38.19%
- Qwen/QwQ-32B-Previewqwen37.94%
- Google: Gemma 2 27Bgoogle36.28%
- google/gemma-2-9b-itgoogle31.74%
- Google: Gemma 3 12Bgoogle29.36%
- meta-llama/Meta-Llama-3-8B-Instructmeta-llama25.54%
- Llama-3-1-8Bmeta-llama24.1%
- Qwen2-7B-Instructqwen23.87%
- Qwen: Qwen2.5 7B Instructqwen21.96%
- lightblue/suzume-llama-3-8B-multilinguallightblue21.95%
ARC Easy
openPersianLLM · Open Persian LLM Leaderboard · ARC Easy · percent · Higher is better
- Google: Gemma 2 27Bgoogle95.98%
- Google: Gemma 3 27Bgoogle95.69%
- Meta: Llama 3.3 70B Instructmeta-llama95.4%
- Google: Gemma 3 12Bgoogle93.39%
- google/gemma-2-9b-itgoogle93.1%
- Qwen/QwQ-32B-Previewqwen91.95%
- Qwen/Qwen2.5-32B-Instructqwen90.8%
- Qwen: Qwen2.5 7B Instructqwen79.02%
- Qwen2-7B-Instructqwen77.3%
- Google: Gemma 3 4Bgoogle77.01%
- NousResearch/Hermes-3-Llama-3.1-8Bnousresearch77.01%
- Llama-3-1-8Bmeta-llama75.28%
ARC Challenge
openPersianLLM · Open Persian LLM Leaderboard · ARC Challenge · percent · Higher is better
AUT Multiple Choice Persian
openPersianLLM · Open Persian LLM Leaderboard · AUT Multiple Choice Persian · percent · Higher is better
- Meta: Llama 3.3 70B Instructmeta-llama71.4%
- Google: Gemma 3 27Bgoogle64.3%
- Google: Gemma 2 27Bgoogle63.12%
- google/gemma-2-9b-itgoogle62.33%
- Qwen/Qwen2.5-32B-Instructqwen61.34%
- Qwen/QwQ-32B-Previewqwen60.15%
- Google: Gemma 3 12Bgoogle57%
- meta-llama/Meta-Llama-3-8B-Instructmeta-llama53.85%
- Llama-3-1-8Bmeta-llama53.45%
- Qwen: Qwen2.5 7B Instructqwen52.66%
- NousResearch/Hermes-3-Llama-3.1-8Bnousresearch52.46%
- Qwen2-7B-Instructqwen51.68%
Models
LoadingBenchmarks
Explore every benchmark
LoadingThese charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.