LA Leaderboard - BEC2016 Basque: leaderboard
Sentiment classification of Basque tweets from the 2016 Basque election campaign (BEC2016eu). From the LA Leaderboard, which evaluates models on Spanish, Catalan, Basque and Galician tasks with the lm-evaluation-harness; F1 (%), higher is better. Each model result file is a separate run.
Metric: F1 (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 9B (IT) | 59.22 | #795 |
| 2 | Gemma 3 4B (IT) | 58.6 | #997 |
| 3 | Llama 3.1 8B Instruct | 58.06 | #1017 |
| 4 | salamandra-7B-instruct | 57.14 | #1392 |
| 5 | Gemma 2 9B | 54.84 | #924 |
| 6 | salamandra-7B | 51.23 | #1446 |
| 7 | Qwen3-8B-Base | 47.24 | #626 |
| 8 | Llama 3.2 3B Instruct | 47.16 | #1327 |
| 9 | Llama 3.1 8B | 47.16 | #1130 |
| 10 | gemma-3-4B-pt Base | 45.7 | #1110 |
| 11 | Yi-1.5-9B Chat | 45.7 | #1032 |
| 12 | Qwen 2.5 7B | 45.16 | #895 |
| 13 | Qwen 2.5 7B Instruct | 44.32 | #863 |
| 14 | salamandra-2B | 44.09 | #1520 |
| 15 | Yi-1.5-9B | 44.01 | #1215 |
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-bec2016-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.