# Moonshot AI — PerceptionBench

- Company: Moonshot AI (moonshot.ai)
- Announced: 2026-07-16T00:00:00+00:00
- Category: research-paper
- Subject: Kimi
- Source: https://www.kimi.ai/blog/perception-bench
- Record: https://forck.live/items/4622-perceptionbench

Moonshot AI releases PerceptionBench, a benchmark for evaluating atomic visual perception in multimodal large language models, with 3,000 verified questions across 10 atomic perceptual categories, and open-sources the dataset and evaluation code.

## Evidence

Verbatim from https://www.kimi.ai/blog/perception-bench:

> 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, not defined in advance.

---

Record: https://forck.live/items/4622-perceptionbench
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md