Sarvam Releases Prism, an Open-Weight Decision Model Built on Sarvam 105B That Returns Calibrated Option Probabilities in About 44 ms, Apache 2.0
Indian AI company Sarvam released Sarvam Prism on November 3, a "System One" decision model for enterprise workflows: given a context and questions with fixed answer options, it returns a probability for every option in a single forward pass instead of generating text. Sarvam says that across the 25 decision models it tested, Prism averages 71.8 over three indices with a median response time of 44 ms on one B200, the highest score under 100 ms, and scores 82.5 on its Indian-language benchmark. Weights are on Hugging Face under Apache 2.0, with a hosted API as well. All scores are Sarvam's own measurements.
Key Takeaways
- Trained on the Sarvam 105B (105B-10B MoE) base; it only outputs option probabilities, so the answer is always one of the given options.
- Vendor-reported indices: Jev Decision Index 67.0, Sarvam's recreation of the Artificial Analysis decision index 65.9, internal Indian-language benchmark 82.5, average 71.8; Perplexity Decider v1.2 averages 68.0 at about 117 ms.
- Calibration: on English answers at 90%+ confidence it expects 3.3% errors and makes 2.2%; in Indian languages 5.4% expected vs 4.4% actual, while rivals underestimate errors by 1.5x to 4.8x.
- By sorting options into a fixed order before scoring, it changed 0 of 2,000 answers across four shuffled option orders.
- On 700 recorded agent runs it judges correctly 78.5% of the time overall, vs 70.7% for Claude Haiku 5.5.
- Self-hosting needs one FP8-capable GPU with about 120 GB free memory (such as B200 or H200) and about 106 GB of disk for weights.
Linked Models & Agents:
⚡ Sarvam Prism⚡ Sarvam 105B⚡ Perplexity Decider v1.2⚡ Jev 1.14⚡ Microsoft-Decision-1⚡ Claude Haiku 5.5🌐 Sarvam
