LA Leaderboard - EusReading Basque: leaderboard
Multiple-choice reading comprehension from Basque language proficiency exams (EusReading). 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 | 62.22 | #924 |
| 2 | Gemma 2 9B (IT) | 59.09 | #795 |
| 3 | Llama 3.1 8B Instruct | 50.85 | #1017 |
| 4 | Llama 3.1 8B | 47.44 | #1130 |
| 5 | Qwen3-8B-Base | 46.88 | #626 |
| 6 | salamandra-7B-instruct | 44.89 | #1392 |
| 7 | gemma-3-4B-pt Base | 38.64 | #1110 |
| 8 | Qwen 2.5 7B | 34.66 | #895 |
| 9 | Llama 3.2 3B Instruct | 34.38 | #1327 |
| 10 | Qwen 2.5 7B Instruct | 32.95 | #863 |
| 11 | Llama 3.2 3B | 32.95 | #1376 |
| 12 | Gemma 3 4B (IT) | 32.67 | #997 |
| 13 | Qwen 2.5 3B Instruct | 32.1 | #1159 |
| 14 | aya-expanse-8B | 31.82 | #914 |
| 15 | Yi-1.5-9B Chat | 31.82 | #1032 |
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-eusreading-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.