Sarvam AI releases open-weight Prism model for enterprise decisions
Sarvam AI launched Prism, an open-weight decision model built on its 105B base, on November 3, 2026. Unlike generative models, Prism scores predefined options in one forward pass without token-by-token generation, targeting enterprise use cases like intent routing, document intelligence, and agent oversight. It achieves a 44-millisecond median response time on a single NVIDIA B200 GPU (FP8…
Key points
- Prism scores predefined options in one pass, targeting enterprise decisions like intent routing and agent oversight
- Achieves **44ms median latency** on a single NVIDIA B200 GPU (FP8) with **71.8** benchmark score
- Open weights under Apache 2.0, hosted on Hugging Face; API access via Sarvam Indus
Prism’s design emphasizes calibration: it uses cross-entropy with 5% label smoothing and Brier loss to reduce overconfidence and penalize costly mistakes. Testing on 226,088 English questions and 20,108 multilingual queries showed error rates below predicted thresholds. For agent evaluation, it scored 78.5% accuracy across 700 recorded runs, excelling in task success (75.0%) and failure attribution (69.6%). Sarvam also highlights 89.0% accuracy on an internal cybersecurity benchmark of 5,517 questions, with plans to release the dataset publicly. The model’s open weights enable enterprises to deploy it on private infrastructure, addressing a gap in AI-driven decision automation.
Model pages: Jev 1.14 → · Microsoft-Decision-1 → · Clef →
Sarvam AI Releases Open-Weight Prism Decision Model
Unite.AI · 4 November 2026
Loading the full article…
This text was published by Unite.AI and written by Jonas Reeve, Cognitive AI & AGI, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Sysdig releases AI Defense to monitor and block agent actions across endpoints and cloud · 1 src
- Sentra raises $150M to secure enterprise data for AI agents · 3 src
- Parloa and Deloitte Canada expand AI agent partnership for Canadian customer service · 1 src
- Cyberhaven partners with MIT Technology Review on data lineage for agentic AI · 1 src
- Nooks secures $500M customer-value financing for Revenue Agent Platform · 2 src
Comments
via GitHub Discussions