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)→
More from Research
- Exponential launches RepoInject and BrowserInject benchmarks for prompt injection robustness — maksym_andr · 2026-10-27
- Redwood: CoT controllability evals are under-elicited; better prompts boost scores 2-3x — dfrsrchtwts · 2026-10-27
- Inverse-designed optical system solves MNIST using BeamZ — S_Conradi · 2026-10-27
- DeCert supervises generative reward models' rationales without reference explanations — Guiquan Sun · 2026-10-27
- VLM harnesses act as compositional generalizers, new blog post shows — a1zhang · 2026-10-27
- Article proposes a Human Genome Project for AI interpretability — ninamiolane · 2026-10-27