LA Leaderboard - OpenBookQA Catalan: leaderboard
Catalan translation of the OpenBookQA elementary science multiple-choice questions. 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-instruct | 34 | #1392 |
| 2 | Mistral 7B Instruct (v0.3) | 32.2 | #1255 |
| 3 | EuroLLM-9B | 31.8 | #1238 |
| 4 | Llama 3.1 8B Instruct | 31.4 | #1017 |
| 5 | Gemma 2 9B (IT) | 31.4 | #795 |
| 6 | aya-expanse-8B | 31 | #914 |
| 7 | Gemma 2 9B | 30.4 | #924 |
| 8 | EuroLLM-9B-Instruct | 30 | #1047 |
| 9 | salamandra-7B | 29.6 | #1446 |
| 10 | Qwen 3 8B | 29 | #678 |
| 11 | Mistral-7B-v0.3 | 28.8 | #1321 |
| 12 | gemma-3-4B-pt Base | 28.6 | #1110 |
| 13 | occiglot-7B-eu5-instruct | 28.6 | |
| 14 | Llama 3.1 8B | 28.2 | #1130 |
| 15 | Qwen3-8B-Base | 27.4 | #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-openbookqa-catalan · How It Works · Data refreshed daily, snapshot 2026-11-05.