Kaggle Global-MMLU-Lite - Italian: leaderboard
Accuracy on the Italian questions (400 on this board) of Cohere Labs' Global-MMLU-Lite leaderboard on Kaggle, an MMLU-derived multilingual multiple-choice set with culturally sensitive and culturally agnostic questions. Shown as 0-100, higher is better; four answer options, so guessing scores about 25.
Metric: Accuracy (%). Source: www.kaggle.com. Saturation forecast: Estimated already saturated. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 97 | #16 |
| 2 | Claude Opus 5.5 | 96.5 | #3 |
| 3 | Gemini 3.7 Flash | 96 | #24 |
| 4 | GPT-6 Sol | 96 | #19 |
| 5 | Gemini 3.8 Flash | 95.75 | #30 |
| 6 | Grok 4.5 | 95.75 | #54 |
| 7 | Gemini 3 Pro (Preview) | 95.5 | #71 |
| 8 | Gemini 4 Argon | 95.5 | #9 |
| 9 | Claude Opus 4.8 | 95.25 | #39 |
| 10 | GPT-5.6 Terra | 95.25 | #40 |
| 11 | Gemini 3.5 Flash | 95 | #66 |
| 12 | GPT-6 Astra | 95 | #6 |
| 13 | GPT-5.6 Sol | 94.75 | #22 |
| 14 | Gemini 3.6 Flash | 94.75 | #57 |
| 15 | GPT-6 Luna | 94 | #61 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=kaggle-global-mmlu-lite-italian · How It Works · Data refreshed daily, snapshot 2026-11-05.