LA Leaderboard - EusProficiency Basque: leaderboard
Multiple-choice questions from Basque language proficiency (EGA) exams (EusProficiency). From the LA Leaderboard, which evaluates models on Spanish, Catalan, Basque and Galician tasks with the lm-evaluation-harness; accuracy (%), higher is better. Each model result file is a separate run.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 9B | 39.39 | #924 |
| 2 | salamandra-7B-instruct | 37.61 | #1392 |
| 3 | Gemma 2 9B (IT) | 36.53 | #795 |
| 4 | gemma-3-4B-pt Base | 33.53 | #1110 |
| 5 | Llama 3.1 8B Instruct | 33.31 | #1017 |
| 6 | Qwen3-8B-Base | 32.64 | #626 |
| 7 | Llama 3.1 8B | 32.04 | #1130 |
| 8 | Gemma 3 4B (IT) | 30.76 | #997 |
| 9 | salamandra-7B | 30.35 | #1446 |
| 10 | Llama 3.2 3B Instruct | 27.08 | #1327 |
| 11 | Gemma 2 2B (IT) | 26.91 | #1328 |
| 12 | SmolLM3-3B-Base | 26.72 | #1260 |
| 13 | Yi-1.5-9B | 26.66 | #1215 |
| 14 | aya-expanse-8B | 26.48 | #914 |
| 15 | Llama 3.2 3B | 26.48 | #1376 |
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-eusproficiency-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.