Decision 3.0: open, multimodal decision models from 0.6B to 27B. Ranks #1 on both Jev Decision Index boards

With the vLLM Semantic Router team we released Decision 3.0 (d3), our new SOTA decision model family ranging from 0.6B to 27B, Apache-2.0, all reading text, images and video. How it works - Built on Qwen3.5 (0.8B / 2B / 4B / 9B) and Qwen3.8-27B. The parameter counts include the vision encoder: 0.33B in the 4B, 0.46B in the 27B. - Three decision types: choice, yes/no, score. Probability for every answer, with no text generation. Several questions about the same input are answered in one call, each from its own forward pass over the input. - Images: multiple per request, read at up to 1.6 MP. - Video: multiple per request (MP4, WebM, MOV, MKV), sampled at 2 fps, at most 32 frames over the whole clip, each at up to 0.2 MP. - BF16 weights, load with Transformers (trust_remote_code=True), trained on AMD Instinct MI325X. Results (our evaluation, official Jev 0.3 kit on the released weights) - #1 on both boards: the 27B scores 64.7 text and 71.6 vision, ahead of every listed model, Jev's own included. - Every size leads its class: the 0.6B, 0.8B, 4B and 9B each lead their size class. The 9B (d3-flash) beats our previous-generation 27B (Decision 2.0). - Video zero-shot: no model saw video in training. On all 19,140 Perception Test validation questions, the 27B scores 77.4 and the 4B scores 70.3. HF collection: https://huggingface.co/collections/vllm-sr/decision-30