LA Leaderboard - xStoryCloze Basque: leaderboard
XStoryCloze story-ending selection in Basque. 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 | 64.86 | #1446 |
| 2 | Gemma 2 9B | 60.16 | #924 |
| 3 | gemma-3-4B-pt Base | 59.43 | #1110 |
| 4 | salamandra-2B | 58.97 | #1520 |
| 5 | Gemma 3 4B (IT) | 56.25 | #997 |
| 6 | salamandra-7B-instruct | 56.25 | #1392 |
| 7 | Gemma 2 9B (IT) | 56.06 | #795 |
| 8 | Llama 3.1 8B | 55.39 | #1130 |
| 9 | Llama 3.1 8B Instruct | 54.86 | #1017 |
| 10 | salamandra-2B-instruct | 54.53 | |
| 11 | gemma-3-1B-pt Base | 53.21 | #1519 |
| 12 | Llama 3.2 3B | 53.08 | #1376 |
| 13 | Gemma 2 2B | 52.81 | #1466 |
| 14 | Gemma 2 2B (IT) | 52.08 | #1328 |
| 15 | Qwen3-8B-Base | 52.02 | #626 |
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-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.