List your company

Instruction Following on Mimic-Instr MIMIC-IV

84.5AccuracyGPT-5
14.09232.37150.6568.929May 10, 2026

Evaluation results

MethodLinks
GPT-5Family=Frontier API2026.0584.5
GPT-4.1Family=Frontier API2026.0565.5
GPT-4.1-miniFamily=Frontier API2026.0563.7
MedGemma-27BFamily=Medical / open-source2026.0562.3
DS-R1-0528Family=Medical / open-source2026.0560.4
CLR-voyance-8BFamily=8B family, Merge Strategy=DELLA-Linear2026.0558.9
HuatuoGPT-o1Family=Medical / open-source2026.0555.1
Qwen3-8B baseFamily=8B family2026.0554.5
Gemma-3-4BFamily=Medical / open-source2026.0542.7
MG-Δ+AFamily=4B family, Merge Strategy=DELLA-Linear+AIM2026.0523.2
CLR-voyance-4BFamily=4B family, Merge Strategy=DELLA-Linear2026.0519.5
MG-B+AFamily=4B family, Merge Strategy=Breadcrumbs+AIM2026.0519.5
MG-4B baseFamily=4B family2026.0519.3
MG-BFamily=4B family, Merge Strategy=Breadcrumbs2026.0519.2
DS-R1-DistillFamily=Medical / open-source2026.0516.8