LatamBoard - OAB Exams: leaderboard
The "OAB Exams" 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 2031. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Hermes-4-14B | 61.82 | #751 |
| 2 | gemma-3-12B-pt | 59.04 | #686 |
| 3 | Qwen 3 VL 8B Instruct | 56.17 | #420 |
| 4 | Qwen 3 VL 4B Instruct | 53.39 | #515 |
| 5 | Phi-3-medium-4k-instruct | 52.03 | #952 |
| 6 | Gemma 3n E4B (IT) | 51.98 | #749 |
| 7 | Llama 3.1 8B Instruct | 51.85 | #1035 |
| 8 | Ministral-8B-Instruct-2410 | 51.48 | #1094 |
| 9 | Qwen 3 4B 2507 Instruct | 51.39 | #762 |
| 10 | Mistral-NeMo-Minitron-8B-Instruct | 51.3 | #907 |
| 11 | Hermes-3-Llama-3.1-8B | 49.02 | #997 |
| 12 | Apertus-8B-Instruct-2509 | 48.88 | #1061 |
| 13 | aya-expanse-8B | 47.65 | #931 |
| 14 | Gemma 3n E2B (IT) | 47.15 | #942 |
| 15 | SOLAR-10.7B-Instruct-v1.0 | 46.83 | #1075 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=latamboard-oab-exams · How It Works · Data refreshed daily, snapshot 2026-10-20.