Evals for Every Language - Maltese (mt): leaderboard
Average score across evaluation tasks in Maltese (mt), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 83.46 | #58 |
| 2 | Claude Sonnet 4.5 | 81.93 | #142 |
| 3 | Gemini 3.1 Flash Lite | 80.94 | #191 |
| 4 | Claude Sonnet 4 | 80.5 | #199 |
| 5 | GPT-5 | 80.3 | #98 |
| 6 | Claude Opus 4.7 | 80.04 | #49 |
| 7 | GPT-5.1 | 79.27 | #135 |
| 8 | GPT-5.3 | 79.15 | #103 |
| 9 | Claude Sonnet 4.6 | 79 | #90 |
| 10 | GPT-5.5 | 77.38 | #31 |
| 11 | Claude Opus 4.8 | 76.93 | #37 |
| 12 | DeepSeek V3.1 | 76.67 | #264 |
| 13 | Gemini 2.5 Pro | 76.07 | #152 |
| 14 | GPT-5.4 | 75.87 | #79 |
| 15 | GPT-4.1 | 75.66 | #248 |
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-mt · How It Works · Data refreshed daily, snapshot 2026-10-20.