LatamBoard - Spanish TeleIA: leaderboard
The "Spanish TeleIA" 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 | gemma-3-12B-pt | 76.19 | #686 |
| 2 | Hermes-4-14B | 76.19 | #751 |
| 3 | Apertus-8B-Instruct-2509 | 71.43 | #1061 |
| 4 | Yi-1.5-9B Chat | 71.43 | #1031 |
| 5 | Gemma 3n E4B (IT) | 71.43 | #749 |
| 6 | Granite 4.0 H 1B | 71.43 | #1191 |
| 7 | SOLAR-10.7B-Instruct-v1.0 | 71.43 | #1075 |
| 8 | aya-vision-8B | 71.43 | #1107 |
| 9 | Llama 3.1 8B Instruct | 66.67 | #1035 |
| 10 | Qwen 3 4B 2507 Instruct | 66.67 | #762 |
| 11 | Qwen 3 VL 4B Instruct | 66.67 | #515 |
| 12 | aya-expanse-8B | 66.67 | #931 |
| 13 | Granite 3.3 8B Instruct | 66.67 | #825 |
| 14 | Phi-3-medium-4k-instruct | 66.67 | #952 |
| 15 | zephyr-7B-beta | 66.67 | #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-teleia · How It Works · Data refreshed daily, snapshot 2026-10-20.