Open Italian LLM - MMLU-Pro (IT) — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3 8B Ita | 30.7 |
| 2 | LLaMAntino-3-ANITA-8B-Inst-DPO-ITA | 30.11 |
| 3 | maestrale-chat-v0.4-beta | 29.15 |
| 4 | Llama 3 8B Instruct | 28.43 |
| 5 | Llama 3 8B 4bit UltraChat Ita | 26.01 |
| 6 | Mistral-7B-v0.1 | 25.04 |
| 7 | Mistral-7B-v0.3 | 24.9 |
| 8 | Volare | 23.61 |
| 9 | occiglot-7B-it-en-instruct | 23.57 |
| 10 | Qwen 2 1.5B Instruct | 20.93 |
| 11 | Qwen2-1.5B-Ita | 20.31 |
| 12 | LLaMAntino-2-7B-hf-ITA | 15.25 |
Interactive version: theaggregate.ai/benchmark?slug=open-italian-llm-mmlu-pro-it · How the rankings work · Data refreshed daily, snapshot 2026-07-22.