List your company

Medical Question Answering on MedQA-de (test)

70.2AccuracyDeFineMed-Mistral-Small-24B-SLERP
35.8844.7953.762.61Apr 21, 2026

Evaluation results

MethodLinks
DeFineMed-Mistral-Small-24B-SLERPEvaluation Setting=one-shot2026.0470.2
Mistral-Small-24B-InstructEvaluation Setting=one-shot2026.0468.8
DeFineMed-Mistral-Small-24BEvaluation Setting=one-shot2026.0468.8
DeFineMed-Qwen2.5-7B-SLERPEvaluation Setting=one-shot2026.0454.2
DeFineMed-Qwen2.5-7BEvaluation Setting=one-shot2026.0452.6
DeFineMed-Mistral-7B-SLERPEvaluation Setting=one-shot2026.0450.2
Qwen2.5-7B-InstructEvaluation Setting=one-shot2026.0450.2
DeFineMed-Mistral-7BEvaluation Setting=one-shot2026.0446.8
Mistral-7B-Instruct-v0.3Evaluation Setting=one-shot2026.0442.4
BioMistral-7B-SLERP (baseline)Evaluation Setting=one-shot2026.0437.6
BioMistral-7B (baseline)Evaluation Setting=one-shot2026.0437.2