Medical Question Answering on Clinical Knowledge German (test)
82.64AccuracyDeFineMed-Mistral-Small-24B-SLERP
Evaluation results
| Method | Links | |
|---|---|---|
| DeFineMed-Mistral-Small-24B-SLERPEvaluation Setting=one-shot2026.04 | 82.64 | |
| DeFineMed-Mistral-Small-24BEvaluation Setting=one-shot2026.04 | 79.62 | |
| Mistral-Small-24B-InstructEvaluation Setting=one-shot2026.04 | 78.87 | |
| DeFineMed-Qwen2.5-7BEvaluation Setting=one-shot2026.04 | 76.6 | |
| DeFineMed-Qwen2.5-7B-SLERPEvaluation Setting=one-shot2026.04 | 75.85 | |
| Qwen2.5-7B-InstructEvaluation Setting=one-shot2026.04 | 69.06 | |
| DeFineMed-Mistral-7B-SLERPEvaluation Setting=one-shot2026.04 | 65.66 | |
| DeFineMed-Mistral-7BEvaluation Setting=one-shot2026.04 | 65.28 | |
| Mistral-7B-Instruct-v0.3Evaluation Setting=one-shot2026.04 | 61.13 | |
| BioMistral-7B-SLERP (baseline)Evaluation Setting=one-shot2026.04 | 58.49 | |
| BioMistral-7B (baseline)Evaluation Setting=one-shot2026.04 | 52.08 |