Evals for Every Language - Portuguese (pt): leaderboard
Average score across evaluation tasks in Portuguese (pt), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around March 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 81.08 | #191 |
| 2 | Claude Sonnet 4.5 | 79.23 | #142 |
| 3 | Gemini 3.1 Pro (Preview) | 79.23 | #58 |
| 4 | Claude Sonnet 4.6 | 78.95 | #90 |
| 5 | Claude Opus 4.8 | 78.9 | #37 |
| 6 | Claude Opus 4.7 | 78.45 | #49 |
| 7 | GPT-5.3 | 78.24 | #103 |
| 8 | Claude Sonnet 4 | 78.23 | #199 |
| 9 | Command A | 77.5 | #508 |
| 10 | Gemini 2.5 Pro | 77.41 | #152 |
| 11 | Gemini 2.5 Flash Lite | 77.09 | #422 |
| 12 | GPT-5 | 76.79 | #98 |
| 13 | Gemma 3 27B (IT) | 76.48 | #523 |
| 14 | Claude Haiku 4.5 | 76.38 | #280 |
| 15 | Llama 3.3 70B Instruct | 76.22 | #534 |
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-pt · How It Works · Data refreshed daily, snapshot 2026-10-20.