{"version":1,"type":"story","url":"https://digestai.news/story/samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research","json":"https://digestai.news/story/samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research.json","markdown":"https://digestai.news/story/samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research.md","slug":"samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research","headline":"Samaya AI launches Sterling agent, claims 11x cheaper finance research than Claude Fable 5.1","summary":"Samaya AI released Sterling, a 3B-active-parameter agent built on NVIDIA’s Nemotron 3.5 Lightning, optimized for financial research. The model scores 58.9% on Samaya’s FrontierFinance benchmark, surpassing Claude Fable 5.1’s 55.9% while costing $0.61 per query versus $6.89. Sterling’s performance stems from co-training the model with its harness, which includes a condenser for long tool results, a compactor for trace summaries, and a research budget cap. Training involved four stages: synthetic trace fine-tuning, expert-graded strategy selection, offline and online GRPO reinforcement, and truncated importance sampling for MoE sampling fixes.\n\nThe model runs on a single H100 80GB GPU in BF16 with up to 1M-token context, though Sterling’s serving context window is undisclosed. Samaya reports Sterling beats every system on FrontierFinance in cost-per-quality, with a median of 17 tool calls per query. High-effort mode achieves 60.6% at $1.83 per question. The company emphasizes its approach—small model, efficient harness—as a scalable recipe for domain-specific agents. All benchmark results are self-reported, and no training data overlaps with FrontierFinance’s 220 public queries.","keyPoints":["Sterling scores 58.9% on FrontierFinance, 3 points above Claude Fable 5.1’s 55.9%, at 11x lower cost per query","Built on NVIDIA’s 30B Nemotron 3.5 Lightning with 3B active parameters, trained via LoRA and GRPO in four stages","Harness includes context tools (condenser, compactor) and a research budget cap to manage agent efficiency"],"whyItMatters":"Sterling demonstrates how co-training a small model with its orchestration tools can outperform larger models in niche tasks like finance research, potentially reducing costs for specialized AI agents.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Samaya AI","NVIDIA","Thinking Machines Lab","MarkTechPost","Marktechpost AI Media Inc."],"models":["Sterling","Nemotron 3.5 Lightning","Claude Fable 5.1","Kimi K3"],"people":["Maithra Raghu","Asif Razzaq"]},"firstPublishedAt":"2026-10-30T07:26:12Z","updatedAt":"2026-10-30T07:26:12Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Samaya AI Releases Sterling: A 3B-Active Finance Research Agent Model that Beats Claude Fable 5.1 on FrontierFinance at 11x Lower Cost","url":"https://marktechpost.com/2026/10/30/samaya-sterling-post-trained-finance-research-model-frontierfinance","publishedAt":"2026-10-30T07:26:12Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Samaya AI launches Sterling agent, claims 11x cheaper finance research than Claude Fable 5.1\", 30 October 2026, https://digestai.news/story/samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research","publisher":"Digest AI","title":"Samaya AI launches Sterling agent, claims 11x cheaper finance research than Claude Fable 5.1","datePublished":"2026-10-30T07:26:12Z","url":"https://digestai.news/story/samaya-ai-launches-sterling-agent-claims-11x-cheaper-finance-research"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}