LA Leaderboard - xStoryCloze Spanish: leaderboard
XStoryCloze story-ending selection in Spanish. 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 | 73.99 | #924 |
| 2 | salamandra-7B | 73.46 | #1446 |
| 3 | occiglot-7B-eu5 | 73.4 | |
| 4 | EuroLLM-9B | 72.01 | #1238 |
| 5 | Llama 3.1 8B | 70.81 | #1130 |
| 6 | SmolLM3-3B-Base | 70.09 | #1260 |
| 7 | gemma-3-4B-pt Base | 69.69 | #1110 |
| 8 | Mistral 7B Instruct (v0.3) | 69.56 | #1255 |
| 9 | Yi-1.5-9B | 69.23 | #1215 |
| 10 | Qwen 2.5 7B | 69.09 | #895 |
| 11 | occiglot-7B-eu5-instruct | 68.96 | |
| 12 | Mistral-7B-v0.3 | 68.63 | #1321 |
| 13 | Qwen 2.5 7B Instruct | 68.56 | #863 |
| 14 | Teuken-7B-instruct-commercial-v0.4 | 68.23 | #1421 |
| 15 | Llama 3.1 8B Instruct | 67.77 | #1017 |
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-spanish · How It Works · Data refreshed daily, snapshot 2026-11-05.