LatamBoard - ENEM Challenge: leaderboard
The "ENEM Challenge" 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 | 83.07 | #751 |
| 2 | Qwen 3 VL 8B Instruct | 80.69 | #420 |
| 3 | gemma-3-12B-pt | 77.96 | #686 |
| 4 | Qwen 3 VL 4B Instruct | 76.35 | #515 |
| 5 | Qwen 3 4B 2507 Instruct | 75.37 | #762 |
| 6 | Phi-3-medium-4k-instruct | 74.39 | #952 |
| 7 | Mistral-NeMo-Minitron-8B-Instruct | 73.41 | #907 |
| 8 | Gemma 3n E4B (IT) | 71.52 | #749 |
| 9 | Llama 3.1 8B Instruct | 71.31 | #1035 |
| 10 | Ministral-8B-Instruct-2410 | 70.96 | #1094 |
| 11 | SOLAR-10.7B-Instruct-v1.0 | 68.51 | #1075 |
| 12 | Gemma 3n E2B (IT) | 67.88 | #942 |
| 13 | Hermes-3-Llama-3.1-8B | 67.39 | #997 |
| 14 | Granite 3.3 8B Instruct | 67.11 | #825 |
| 15 | Apertus-8B-Instruct-2509 | 66.97 | #1061 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=latamboard-enem-challenge · How It Works · Data refreshed daily, snapshot 2026-10-20.