LA Leaderboard - QNLI Basque: leaderboard
Question-sentence entailment in Basque: whether a sentence answers a question (QNLIeu). 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) | 66.81 | #795 |
| 2 | Gemma 3 4B (IT) | 59.66 | #997 |
| 3 | gemma-3-4B-pt Base | 57.98 | #1110 |
| 4 | Qwen 3 8B | 57.14 | #678 |
| 5 | Gemma 2 9B | 57.14 | #924 |
| 6 | Qwen3-8B-Base | 56.3 | #626 |
| 7 | salamandra-7B | 55.46 | #1446 |
| 8 | Teuken-7B-instruct-commercial-v0.4 | 55.46 | #1421 |
| 9 | aya-expanse-8B | 55.04 | #914 |
| 10 | Mistral 7B Instruct (v0.3) | 54.62 | #1255 |
| 11 | SmolLM2-1.7B-Instruct | 54.62 | #1541 |
| 12 | Llama 3.1 8B Instruct | 54.2 | #1017 |
| 13 | Gemma 3 1B (IT) | 54.2 | #1481 |
| 14 | DeepSeek R1 Distill Qwen 1.5B | 53.78 | #1521 |
| 15 | SmolLM3-3B | 53.78 | #1239 |
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-qnli-basque · How It Works · Data refreshed daily, snapshot 2026-11-05.