EVALITA - MAIA-MC: leaderboard
The "MAIA-MC" subtask of EVALITA. A task from EVALITA, the periodic evaluation campaign for Italian-language natural language processing and understanding.
Metric: CPS. Source: huggingface.co. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 32B Instruct | 87.26 | #453 |
| 2 | Qwen 2.5 VL 7B Instruct | 81.77 | #654 |
| 3 | Gemma 3 27B (IT) | 81.43 | #523 |
| 4 | Pixtral-12B | 80.27 | #808 |
| 5 | aya-vision-8B | 75.88 | #1107 |
| 6 | Gemma 3 4B (IT) | 69.32 | #992 |
| 7 | GLM-4.1V-9B (Thinking) | 59.61 | #472 (GLM-4.1V-9B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evalita-maia-mc · How It Works · Data refreshed daily, snapshot 2026-10-20.