LA Leaderboard - HumorQA: leaderboard
Spanish humour question answering (HumorQA). 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 | Mistral 7B Instruct (v0.3) | 60.78 | #1255 |
| 2 | Qwen 2.5 7B Instruct | 58.82 | #863 |
| 3 | Gemma 2 9B (IT) | 58.82 | #795 |
| 4 | Llama 3.1 8B | 58.82 | #1130 |
| 5 | Qwen 2.5 1.5B Instruct | 58.82 | #1393 |
| 6 | Llama 3.2 1B | 58.82 | #1540 |
| 7 | gemma-3-4B-pt Base | 58.82 | #1110 |
| 8 | Qwen 2.5 7B | 58.82 | #895 |
| 9 | Gemma 2 9B | 58.82 | #924 |
| 10 | Llama 3.2 3B | 58.82 | #1376 |
| 11 | gemma-3-1B-pt Base | 58.82 | #1519 |
| 12 | salamandra-7B | 58.82 | #1446 |
| 13 | Qwen 2.5 1.5B | 58.82 | #1412 |
| 14 | SmolLM3-3B-Base | 58.82 | #1260 |
| 15 | Gemma 2 2B | 58.82 | #1466 |
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-humorqa · How It Works · Data refreshed daily, snapshot 2026-11-05.