Kaggle MultiLoKo - Italian: leaderboard
Metric: Exact Match (%). Source: www.kaggle.com. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71.77 |
| 2 | Gemini 3.5 Flash | 68.27 |
| 3 | Gemini 3 Flash (Preview) | 66.4 |
| 4 | Gemini 2.5 Pro (Preview 06-05) | 56.4 |
| 5 | GPT-5 | 55.2 |
| 6 | O3 | 54 |
| 7 | O1 | 52 |
| 8 | GPT-4o (2024-08-06) | 44 |
| 9 | Gemini 2.5 Flash (Preview 05-20) | 44 |
| 10 | GPT-5.4 | 43.6 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 43.2 |
| 12 | GPT-4.1 | 40.8 |
| 13 | Claude 3.5 Sonnet (20241022) | 38.8 |
| 14 | Claude 3.7 Sonnet | 36.4 |
| 15 | O4 Mini | 36 |
Interactive version: theaggregate.ai/benchmark?slug=kaggle-multiloko-italian · How It Works · Data refreshed daily, snapshot 2026-09-19.