Qwen3.5-9B

EviScene uses agents to assess image factuality rather than only asking whether an image is AI.

EviScene trains Qwen3.5-9B to inspect images, search evidence, compare findings, and verify facts, improving E…

Microsoft's Decision-1 model joins the rapidly expanding AI decision-model competition

Microsoft Decision-1, built on Qwen3.5-9B, leads 36 benchmarks with 83.5% accuracy, 85 ms latency, and $0.042 …