Atlas

Models

← All models

Kimi-VL-A3B-Thinking

Moonshot AI · 2025-04-10 · 16.4B parameters

Kimi-VL-A3B-Thinking is Moonshot AI's open-weight long-thinking Mixture-of-Experts vision-language checkpoint, released with the Kimi-VL technical report in April 2025. It adds long chain-of-thought supervised fine-tuning and reinforcement learning for multimodal reasoning atop a native-resolution MoonViT encoder, MLP projector, and MoE language decoder; the official report describes 2.8B activated language-model parameters plus a 400M vision encoder and a 131,072-token extended context window.

Benchmark scores

BenchmarkScore
MATH-Vision36.8
OSWorld-Verified10.3
Loading Atlas data…