List your company

Scientific Reasoning on Scientific Reasoning Subset A

14.7ROUGE-LBioProAgent
7.8369.61811.413.182Mar 1, 2026

Evaluation results

MethodLinks
BioProAgentBackbone=Gemini-3-Flash2026.0314.734.459.171.8
DirectBackbone=Gemini-3-Flash2026.031324.732.212.1
DirectBackbone=DeepSeek-V32026.0312.32628.552.1
ReflexionBackbone=Gemini-3-Flash2026.0311.828.243.9148.4
ReActBackbone=Gemini-3-Flash2026.0311.626.845.544.5
AutoGPTBackbone=Gemini-3-Flash2026.0311.625.842.9119.6
DirectBackbone=GPT-4o2026.0310.720.218.913.8
BiomniBackbone=(Specialized)2026.038.125.234.287.1