LA Leaderboard - COPA Spanish: leaderboard
The "COPA Spanish" subtask of LA Leaderboard. Iberian and Basque language evaluation: tests LLMs on COPA, PiQA, Belebele, and other NLU tasks in Spanish, Catalan, Basque, and Galician.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 9B (IT) | 89.4 | #788 |
| 2 | EuroLLM-9B-Instruct | 86.2 | #1054 |
| 3 | Llama 3.1 8B Instruct | 86 | #1035 |
| 4 | occiglot-7B-eu5-instruct | 86 | |
| 5 | EuroLLM-9B | 85.2 | #1254 |
| 6 | Gemma 2 9B | 84.4 | #958 |
| 7 | SmolLM3-3B | 84.2 | #1252 |
| 8 | aya-expanse-8B | 84 | #931 |
| 9 | occiglot-7B-eu5 | 84 | |
| 10 | Qwen 2.5 7B Instruct | 83.2 | #862 |
| 11 | Teuken-7B-Instruct-v0.4 | 82.8 | #1430 |
| 12 | Qwen3-8B-Base | 82.4 | #626 |
| 13 | Gemma 3 4B (IT) | 82.2 | #992 |
| 14 | SmolLM3-3B-Base | 82 | #1285 |
| 15 | Mistral 7B Instruct (v0.3) | 81.6 | #1274 |
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-copa-spanish · How It Works · Data refreshed daily, snapshot 2026-10-20.