Gemini Omni Flash 1.2 debuts at #1 on our Relative Camera Movement benchmark! 🥇
Backed by 900K+ human judgments, this benchmark evaluates how well models navigate from a single image to scene-relative viewpoints, like behind a sofa, into the driver’s seat, or from a dog’s
6K+ human judgements/minute via API for Online RLHF and Benchmarks.
Advancing SOTA GenAI research through weekly, open benchmarks → benchmark.ai

