LA Leaderboard - TE-ca: leaderboard
Textual entailment on Catalan sentence pairs (TE-ca). 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 | 53.19 | #1392 |
| 2 | Gemma 2 9B | 52.57 | #924 |
| 3 | EuroLLM-9B | 52.24 | #1238 |
| 4 | Gemma 2 9B (IT) | 52.15 | #795 |
| 5 | Qwen3-8B-Base | 51.72 | #626 |
| 6 | occiglot-7B-eu5 | 51.72 | |
| 7 | Mistral-7B-v0.3 | 51.2 | #1321 |
| 8 | Llama 3.1 8B | 50.21 | #1130 |
| 9 | occiglot-7B-eu5-instruct | 50.12 | |
| 10 | salamandra-7B | 50.07 | #1446 |
| 11 | EuroLLM-9B-Instruct | 48.94 | #1047 |
| 12 | Mistral 7B Instruct (v0.3) | 48.37 | #1255 |
| 13 | Teuken-7B-Instruct-v0.4 | 48.23 | #1408 |
| 14 | Qwen 2.5 7B | 47.95 | #895 |
| 15 | salamandra-2B-instruct | 47.85 |
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-te-ca · How It Works · Data refreshed daily, snapshot 2026-11-05.