Model Releases

We are releasing PerceptionBench, a benchmark that isolates visual perception and evaluates it as a set of atomic capabilities - discovered …

We are releasing PerceptionBench, a benchmark that isolates visual perception and evaluates it as a set of atomic capabilities - discovered from how today's models fail, rather than defined in advance

DGX agentx-post
model-releaseskimi-moonshot--x

We are releasing PerceptionBench, a benchmark that isolates visual perception and evaluates it as a set of atomic capabilities - discovered from how today's models fail, rather than defined in advance. From frontier-model failures across 42 benchmarks, we derive 10 atomic perceptual capabilities and construct 3,000 verified questions, each isolating a single capability and answerable by looking, with no reasoning or external knowledge required. Blog: http://kimi.com/blog/perception-bench GitHub: http://github.com/MoonshotAI/PerceptionBench Hugingface: http://huggingface.co/datasets/moonshotai/PerceptionBench

Source: Kimi/Moonshot (X) | 2026-07-27

Loading related sources…