List your company

Medical Question Answering on HealthBench Medical

56.36ScoreEvoRubric
41.654445.472249.2953.1078May 28, 2026

Evaluation results

MethodLinks
EvoRubricBackbone=Qwen3-14B2026.0556.36
External Evolving-RLBackbone=Qwen3-14B2026.0554.54
EvoRubricBackbone=Qwen3-8B2026.0553.97
Static Rubric-RLBackbone=Qwen3-14B2026.0552.45
Gemini-2.5-proBackbone=Proprietary2026.0551.07
External Evolving-RLBackbone=Qwen3-8B2026.0548.77
Static Rubric-RLBackbone=Qwen3-8B2026.0547.28
GPT-4oBackbone=Proprietary2026.0546.98
Base ModelBackbone=Qwen3-14B2026.0546.36
Base ModelBackbone=Qwen3-8B2026.0542.22