List your company

Paper Understanding on ELAIPBench

43.7ScoreAgentSPEX
33.40436.07738.7541.423Apr 14, 2026

Evaluation results

MethodLinks
AgentSPEXModel=GPT-5*, Domain=Paper Understanding2026.0443.7
CoTModel=GPT-5*, Domain=Paper Understanding2026.0437.22
ReActModel=GPT-5*, Domain=Paper Understanding2026.0433.8