LatamBoard - Spanish OpenBookQA: leaderboard
The "Spanish OpenBookQA" 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 | 40 | #952 |
| 2 | Apertus-8B-Instruct-2509 | 39.4 | #1061 |
| 3 | Gemma 3n E4B (IT) | 38.8 | #749 |
| 4 | Ministral-8B-Instruct-2410 | 38.8 | #1094 |
| 5 | SOLAR-10.7B-Instruct-v1.0 | 38.8 | #1075 |
| 6 | Mistral-NeMo-Minitron-8B-Instruct | 38 | #907 |
| 7 | Hermes-3-Llama-3.1-8B | 37.2 | #997 |
| 8 | aya-expanse-8B | 36.6 | #931 |
| 9 | Granite 4.0 H 1B | 36.4 | #1191 |
| 10 | Seed-X-PPO-7B | 35.8 | #575 |
| 11 | Granite 3.3 8B Instruct | 35.6 | #825 |
| 12 | zephyr-7B-beta | 35.6 | #1330 |
| 13 | Hermes-4-14B | 35.4 | #751 |
| 14 | Llama 3.1 8B Instruct | 35.2 | #1035 |
| 15 | Qwen 3 VL 8B Instruct | 35 | #420 |
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-openbookqa · How It Works · Data refreshed daily, snapshot 2026-10-20.