LA Leaderboard - PIQA Catalan: leaderboard
The "PIQA Catalan" 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 | 70.24 | #958 |
| 2 | salamandra-7B-instruct | 69.97 | #1411 |
| 3 | salamandra-7B | 69.64 | #1461 |
| 4 | EuroLLM-9B | 69.21 | #1254 |
| 5 | Gemma 2 9B (IT) | 68.55 | #788 |
| 6 | EuroLLM-9B-Instruct | 68.44 | #1054 |
| 7 | Llama 3.1 8B Instruct | 67.79 | #1035 |
| 8 | Mistral 7B Instruct (v0.3) | 67.25 | #1274 |
| 9 | Llama 3.1 8B | 66.32 | #1151 |
| 10 | gemma-3-4B-pt Base | 65.18 | #1134 |
| 11 | Mistral-7B-v0.3 | 65.13 | #1355 |
| 12 | occiglot-7B-eu5-instruct | 65.02 | |
| 13 | Qwen3-8B-Base | 64.85 | #626 |
| 14 | salamandra-2B-instruct | 64.31 | |
| 15 | Qwen 3 8B | 63.87 | #674 |
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-piqa-catalan · How It Works · Data refreshed daily, snapshot 2026-10-20.