LA Leaderboard - WNLI Spanish: leaderboard
Spanish translation of WNLI, Winograd-schema pronoun resolution posed as entailment. 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) | 76.06 | #795 |
| 2 | Qwen 2.5 3B Instruct | 70.42 | #1159 |
| 3 | Qwen 2.5 7B | 70.42 | #895 |
| 4 | Qwen3-8B-Base | 70.42 | #626 |
| 5 | Qwen 2.5 7B Instruct | 69.01 | #863 |
| 6 | aya-expanse-8B | 69.01 | #914 |
| 7 | OLMo-2-1124-7B | 69.01 | #1381 |
| 8 | Llama 3.1 8B Instruct | 66.2 | #1017 |
| 9 | SmolLM3-3B | 66.2 | #1239 |
| 10 | Llama 3.2 3B Instruct | 64.79 | #1327 |
| 11 | EuroLLM-9B-Instruct | 64.79 | #1047 |
| 12 | Mistral 7B Instruct (v0.3) | 61.97 | #1255 |
| 13 | Gemma 2 2B (IT) | 61.97 | #1328 |
| 14 | Qwen 2.5 3B | 61.97 | #1177 |
| 15 | Yi-1.5-9B | 60.56 | #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-wnli-spanish · How It Works · Data refreshed daily, snapshot 2026-11-05.