LA Leaderboard - Spanish Law Exams: leaderboard
The "Spanish Law Exams" subtask of LA Leaderboard. Iberian and Basque language evaluation: tests LLMs on COPA, PiQA, Belebele, and other NLU tasks in Spanish, Catalan, Basque, and Galician.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around 2029. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 9B (IT) | 47.9 | #788 |
| 2 | occiglot-7B-eu5-instruct | 42.02 | |
| 3 | Llama 3.2 3B Instruct | 40.34 | #1352 |
| 4 | Mistral 7B Instruct (v0.3) | 40.34 | #1274 |
| 5 | Llama 3.1 8B Instruct | 39.5 | #1035 |
| 6 | Qwen 2.5 7B | 39.5 | #922 |
| 7 | Yi-1.5-9B Chat | 39.5 | #1031 |
| 8 | Qwen 3 4B | 38.66 | #829 |
| 9 | salamandra-7B-instruct | 38.66 | #1411 |
| 10 | Qwen 2.5 7B Instruct | 37.82 | #862 |
| 11 | Qwen3-8B-Base | 37.82 | #626 |
| 12 | aya-expanse-8B | 35.29 | #931 |
| 13 | EuroLLM-9B-Instruct | 35.29 | #1054 |
| 14 | Qwen 2.5 3B | 34.45 | #1211 |
| 15 | SmolLM3-3B-Base | 33.61 | #1285 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=la-leaderboard-spanish-law-exams · How It Works · Data refreshed daily, snapshot 2026-10-20.