SciArena to Shut Down on July 15

allen_ai · x · 2026-07-16

Allen AI introduced SciArena, an evaluation platform designed to test how well AI models handle scientific literature questions, with researchers judging the answer quality.

The project will retire on July 15. It ultimately engaged around 1,700 名用户 who cast approximately 3,900 张票. They plan to use these results to compile researcher feedback on model answers.

Related event: Allen AI retires SciArena; o3 tops the science-QA leaderboard(6 posts)→

Original post →

More from Research

Research channel →