LA Leaderboard - xStoryCloze Galician: leaderboard
XStoryCloze story-ending selection in Galician. 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 | salamandra-7B | 72.8 | #1446 |
| 2 | EuroLLM-9B | 70.75 | #1238 |
| 3 | Gemma 2 9B | 69.89 | #924 |
| 4 | EuroLLM-9B-Instruct | 66.78 | #1047 |
| 5 | gemma-3-4B-pt Base | 65.85 | #1110 |
| 6 | salamandra-7B-instruct | 64.99 | #1392 |
| 7 | Llama 3.1 8B | 64.33 | #1130 |
| 8 | salamandra-2B | 62.94 | #1520 |
| 9 | Gemma 2 9B (IT) | 62.67 | #795 |
| 10 | Llama 3.1 8B Instruct | 61.88 | #1017 |
| 11 | Yi-1.5-9B | 61.88 | #1215 |
| 12 | Qwen 2.5 7B | 60.89 | #895 |
| 13 | Llama 3.2 3B | 60.89 | #1376 |
| 14 | Qwen 2.5 7B Instruct | 60.62 | #863 |
| 15 | occiglot-7B-eu5 | 60.62 |
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-xstorycloze-galician · How It Works · Data refreshed daily, snapshot 2026-11-05.