LA Leaderboard - COPA Catalan: leaderboard
Catalan translation of COPA: choosing the more plausible cause or effect of a premise. 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) | 82 | #795 |
| 2 | EuroLLM-9B-Instruct | 82 | #1047 |
| 3 | Llama 3.1 8B Instruct | 81.4 | #1017 |
| 4 | salamandra-7B-instruct | 81.2 | #1392 |
| 5 | EuroLLM-9B | 80.8 | #1238 |
| 6 | salamandra-7B | 80 | #1446 |
| 7 | Gemma 2 9B | 78.2 | #924 |
| 8 | Mistral 7B Instruct (v0.3) | 77.6 | #1255 |
| 9 | Llama 3.1 8B | 77 | #1130 |
| 10 | Qwen3-8B-Base | 76.8 | #626 |
| 11 | gemma-3-4B-pt Base | 74.8 | #1110 |
| 12 | Gemma 3 4B (IT) | 74.6 | #997 |
| 13 | Mistral-7B-v0.3 | 74 | #1321 |
| 14 | Qwen 3 8B | 73.4 | #678 |
| 15 | occiglot-7B-eu5-instruct | 72.4 |
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-catalan · How It Works · Data refreshed daily, snapshot 2026-11-05.