LA Leaderboard - OpenBookQA Spanish: leaderboard
Spanish 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 | EuroLLM-9B | 37.8 | #1238 |
| 2 | salamandra-7B-instruct | 36.2 | #1392 |
| 3 | SmolLM3-3B-Base | 36.2 | #1260 |
| 4 | occiglot-7B-eu5 | 36.2 | |
| 5 | EuroLLM-9B-Instruct | 35.2 | #1047 |
| 6 | Mistral 7B Instruct (v0.3) | 35 | #1255 |
| 7 | occiglot-7B-eu5-instruct | 35 | |
| 8 | Llama 3.1 8B | 34.8 | #1130 |
| 9 | Llama 3.1 8B Instruct | 34 | #1017 |
| 10 | Gemma 2 9B | 34 | #924 |
| 11 | Teuken-7B-instruct-commercial-v0.4 | 34 | #1421 |
| 12 | Teuken-7B-Instruct-v0.4 | 33.8 | #1408 |
| 13 | Qwen 2.5 7B | 33 | #895 |
| 14 | salamandra-7B | 32.8 | #1446 |
| 15 | Qwen3-8B-Base | 32.6 | #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-spanish · How It Works · Data refreshed daily, snapshot 2026-11-05.