LA Leaderboard - ClinDiagnosES: leaderboard
Spanish clinical cases for which the model writes the diagnosis (ClinDiagnosES). From the LA Leaderboard, which evaluates models on Spanish, Catalan, Basque and Galician tasks with the lm-evaluation-harness; semantic answer similarity, the cosine similarity of sentence embeddings x100, higher is better. Each model result file is a separate run.
Metric: Semantic Answer Similarity (x100). Source: huggingface.co. Saturation forecast: Estimated already saturated. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 2 9B (IT) | 66.38 | #795 |
| 2 | Gemma 3 4B (IT) | 65.33 | #997 |
| 3 | Qwen 2.5 7B Instruct | 64.16 | #863 |
| 4 | Teuken-7B-Instruct-v0.4 | 63.81 | #1408 |
| 5 | Llama 3.1 8B Instruct | 63.5 | #1017 |
| 6 | Gemma 2 2B (IT) | 62.78 | #1328 |
| 7 | EuroLLM-9B-Instruct | 61.81 | #1047 |
| 8 | Llama 3.1 8B | 61.41 | #1130 |
| 9 | salamandra-7B-instruct | 60.77 | #1392 |
| 10 | Mistral 7B Instruct (v0.3) | 60.27 | #1255 |
| 11 | Llama 3.2 3B Instruct | 60.21 | #1327 |
| 12 | OLMo-2-1124-7B-Instruct | 59.78 | #1343 |
| 13 | Teuken-7B-instruct-commercial-v0.4 | 59.73 | #1421 |
| 14 | occiglot-7B-eu5-instruct | 59.3 | |
| 15 | Gemma 3 1B (IT) | 59.02 | #1481 |
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-clindiagnoses · How It Works · Data refreshed daily, snapshot 2026-11-05.