LA Leaderboard - EusTrivia Basque: leaderboard
Multiple-choice Basque trivia questions (EusTrivia). 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 (IT) | 51.37 | #795 |
| 2 | Gemma 2 9B | 51.02 | #924 |
| 3 | salamandra-7B-instruct | 49.8 | #1392 |
| 4 | Qwen3-8B-Base | 48.34 | #626 |
| 5 | salamandra-7B | 47.99 | #1446 |
| 6 | Llama 3.1 8B Instruct | 46.01 | #1017 |
| 7 | Llama 3.1 8B | 44.49 | #1130 |
| 8 | gemma-3-4B-pt Base | 43.67 | #1110 |
| 9 | Qwen 2.5 7B | 42.33 | #895 |
| 10 | Gemma 3 4B (IT) | 42.22 | #997 |
| 11 | Qwen 2.5 3B | 41.92 | #1177 |
| 12 | Qwen 2.5 7B Instruct | 41.57 | #863 |
| 13 | Llama 3.2 3B Instruct | 39.48 | #1327 |
| 14 | Yi-1.5-9B | 38.83 | #1215 |
| 15 | EuroLLM-9B-Instruct | 38.83 | #1047 |
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-eustrivia-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.