LatamBoard - Spanish Escola: leaderboard
The "Spanish Escola" 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: Not forecast. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Phi-3-medium-4k-instruct | 74.55 | #952 |
| 2 | Gemma 3n E4B (IT) | 71.89 | #749 |
| 3 | AFM-4.5B | 71.32 | #1372 |
| 4 | Qwen 3 VL 8B Instruct | 71.23 | #420 |
| 5 | Yi-1.5-9B Chat | 71.04 | #1031 |
| 6 | Hermes-3-Llama-3.1-8B | 70.85 | #997 |
| 7 | Apertus-8B-Instruct-2509 | 70.66 | #1061 |
| 8 | aya-expanse-8B | 70.66 | #931 |
| 9 | Granite 4.0 H 1B | 70.37 | #1191 |
| 10 | SOLAR-10.7B-Instruct-v1.0 | 70.28 | #1075 |
| 11 | Gemma 3n E2B (IT) | 69.9 | #942 |
| 12 | Llama 3.1 8B Instruct | 69.23 | #1035 |
| 13 | Qwen 3 4B 2507 Instruct | 67.14 | #762 |
| 14 | Qwen 3 VL 4B Instruct | 67.05 | #515 |
| 15 | zephyr-7B-beta | 66.95 | #1330 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=latamboard-spanish-escola · How It Works · Data refreshed daily, snapshot 2026-10-20.