LatamBoard - Portuguese Score: leaderboard
The "Portuguese Score" subtask of LatamBoard. Leaderboard for model performance on Latin American and Iberian language tasks, including Spanish and Portuguese understanding, TELEIA Spanish exams, FLORES/OPUS translation, and structured or image extraction.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Hermes-4-14B | 90.81 | #751 |
| 2 | Qwen 3 VL 8B Instruct | 90.29 | #420 |
| 3 | Qwen 3 VL 4B Instruct | 89.58 | #515 |
| 4 | Qwen 3 4B 2507 Instruct | 88.39 | #762 |
| 5 | SOLAR-10.7B-Instruct-v1.0 | 87.15 | #1075 |
| 6 | Phi-3-medium-4k-instruct | 87.11 | #952 |
| 7 | gemma-3-12B-pt | 87.03 | #686 |
| 8 | Granite 3.3 8B Instruct | 86.96 | #825 |
| 9 | Apertus-8B-Instruct-2509 | 86.75 | #1061 |
| 10 | Gemma 3n E4B (IT) | 86.54 | #749 |
| 11 | Hermes-3-Llama-3.1-8B | 86.22 | #997 |
| 12 | Llama 3.1 8B Instruct | 86.11 | #1035 |
| 13 | Ministral-8B-Instruct-2410 | 86.04 | #1094 |
| 14 | aya-vision-8B | 85.93 | #1107 |
| 15 | Gemma 3n E2B (IT) | 85.57 | #942 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=latamboard-portuguese-score · How It Works · Data refreshed daily, snapshot 2026-10-20.