vLLM Semantic Router releases d3-ultra, a 27B open-weight multimodal decision model
vLLM Semantic Router has released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once and returns probabilities for every answer. The team reports a score of 87.2 on its SR-Text test.
vLLM Semantic Router has released d3-ultra, a 27B open-weight multimodal decision model, according to a MarkTechPost report published October 26, 2026.
What is confirmed
- Parameters: 27B
- License type: open-weight
- Inputs: text, images and video
- Behavior: the model reads the input once, then returns probabilities for every answer
- Benchmark: 87.2 on SR-Text, which the report describes as the team's own test
Reported behavior
Per the report, d3-ultra processes text, images and video in a single pass and outputs a probability for each possible answer, rather than a single generated response. The 87.2 SR-Text score is the team's own result on its own test.
What this means
d3-ultra pairs an open-weight 27B model with multimodal input and probability outputs across all answers. The SR-Text score of 87.2 comes from the team's own test, so it should be read as a self-reported figure.
Related Articles
iFLYTEK Healthcare Upgrades Spark Medical Model to V3.7, Claims 99.6 on MedBench 5.0
iFLYTEK Healthcare announced on October 22 a full upgrade of its Spark medical large model to V3.7, and reports a score of 99.6 on MedBench 5.0. The company says the model now combines speech, medical imaging and language understanding for clinical agent use. The benchmark and usage figures are company-reported.
Kimi K3.1 Pro launches with 1M-token context, 65.7% on Terminal-Bench 4.0; open weights due by Nov 4
Kimi K3.1 Pro, the first model in the K3.1 series, is a 3T-class open-weight model with a 1-million-token context window. It scores 65.7% on Terminal-Bench 4.0 and is available today on Kimi.com, Kimi Work, Kimi Code and the Kimi API. Full weights will be released by Nov 4.
DeepSeek V4.1 Flash 1017: $0.15/$0.6 per 1M tokens, 1M context, 67% hallucination rate on non-answers
DeepSeek has upgraded its open-weight V4.1 Flash to revision 1017, a 552B-parameter MoE model with 16B active parameters and a 1 million token context window. Off-peak API pricing is $0.15 per 1M input tokens and $0.6 per 1M output tokens. Artificial Analysis data shows strong intelligence scores but weak results on hallucination.
Tencent Hunyuan open-sources Hy-SimulMT, a 30B-A3B speech-to-speech interpreter with about 3 seconds of lag
Tencent Hunyuan has open-sourced Hy-SimulMT, a 30B-A3B mixture-of-experts model that translates Chinese and English speech in real time while cloning the speaker's voice. Tencent reports about 3 seconds of StreamLAAL lag on the long-form RealSI benchmark, the lowest among the systems it compared. The weights are listed under Apache 2.0.
Comments
Loading...