Evals for Every Language - Italian (it): leaderboard
Average score across evaluation tasks in Italian (it), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 78.71 | #49 |
| 2 | Gemini 3.1 Pro (Preview) | 78.46 | #58 |
| 3 | Claude Sonnet 4.5 | 78.41 | #142 |
| 4 | Claude Opus 4.8 | 78.35 | #37 |
| 5 | Claude Sonnet 4.6 | 77.97 | #90 |
| 6 | Claude Sonnet 4 | 77.86 | #199 |
| 7 | GPT-5.1 | 77.8 | #135 |
| 8 | Grok 4.20 | 77.39 | #175 |
| 9 | Claude Haiku 4.5 | 76.94 | #280 |
| 10 | Gemini 3.1 Flash Lite | 76.87 | #191 |
| 11 | Mistral Medium 3.1 | 76.51 | #408 |
| 12 | Gemini 2.5 Pro | 76.11 | #152 |
| 13 | GPT-5.2 | 75.81 | #110 |
| 14 | GPT-5.3 | 75.73 | #103 |
| 15 | GPT-5 | 75.52 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-it · How It Works · Data refreshed daily, snapshot 2026-10-20.