List your company
ResearchFormerly WizWand

Medical Question Answering on LLMMed-Eval Medical

79.61ScoreGemini-2.5-pro
66.81870.13973.4676.781May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Gemini-2.5-proBackbone=Proprietary2026.0579.61
External Evolving-RLBackbone=Qwen3-14B2026.0573.76
EvoRubricBackbone=Qwen3-14B2026.0573.46
GPT-4oBackbone=Proprietary2026.0572.71
Static Rubric-RLBackbone=Qwen3-14B2026.0572.36
Base ModelBackbone=Qwen3-14B2026.0571.36
EvoRubricBackbone=Qwen3-8B2026.0570.76
Static Rubric-RLBackbone=Qwen3-8B2026.0569.26
Base ModelBackbone=Qwen3-8B2026.0568.06
External Evolving-RLBackbone=Qwen3-8B2026.0567.31